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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values and their relationships

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

    Tilde symbol followed by letters

    np_acts-logits-general · gemini-2.0-flash

    spectral peaks and chemical groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.58
     initComponents
    -0.57
    Autoritní
    -0.54
     ſche
    -0.53
    GEBURTS
    -0.52
     ProtoMessage
    -0.51
    ंदीखरीदारी
    -0.48
     ſon
    -0.48
     perſon
    -0.47
     estekak
    -0.46
    POSITIVE LOGITS
    $_['
    0.48
    rxjs
    0.41
    ⓧ
    0.40
     fast
    0.40
    ">—
    0.39
     secured
    0.38
     highly
    0.38
     favor
    0.37
     habría
    0.37
    灰
    0.37
    Act Density 0.945%

    No Known Activations