Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific articles and researchers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    chemical formulas or scientific data involving "H"

    np_acts-logits-general · gemini-2.0-flash

    H followed by project/dataset names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     historical
    -0.71
    Historical
    -0.66
    historical
    -0.61
    matorium
    -0.57
    tilizers
    -0.57
    rolid
    -0.57
    וויק
    -0.57
     historic
    -0.57
    horizontal
    -0.55
    cestershire
    -0.54
    POSITIVE LOGITS
    IntoConstraints
    0.70
    SequentialGroup
    0.67
     Heroes
    0.63
     kaarangay
    0.63
     pylori
    0.62
     sapiens
    0.62
    UnusedPrivate
    0.61
     Signalez
    0.61
     HHS
    0.60
     HRS
    0.60
    Act Density 1.346%

    No Known Activations