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

    Neuronpedia

    INDEX
    Explanations

    string formatting and output messages in code

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

    Formatting or punctuation related tokens

    np_acts-logits-general · gemini-2.0-flash

    text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.66
    ########.
    -0.60
     وصلة
    -0.55
     الرياضيه
    -0.53
     kaarangay
    -0.53
     semej
    -0.52
     seguida
    -0.52
    inSlope
    -0.51
     Numerade
    -0.50
     Winaray
    -0.50
    POSITIVE LOGITS
    findpost
    0.69
    format
    0.61
    Notae
    0.55
    mpotent
    0.55
    lossians
    0.52
    ouns
    0.49
    ("}");
    0.49
    gley
    0.48
    EndGlobalSection
    0.48
    mmation
    0.48
    Act Density 0.110%

    No Known Activations