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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing methods or approaches to accomplish goals

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

    find a way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Haute
    -0.39
    Reprints
    -0.33
     co
    -0.33
    rxjs
    -0.32
     print
    -0.31
     ग्राहक
    -0.29
     haute
    -0.29
    夕
    -0.29
     read
    -0.28
     javax
    -0.28
    POSITIVE LOGITS
     Италијани
    0.77
     pinulongan
    0.69
    LookAnd
    0.69
     يتيمه
    0.68
    featureID
    0.65
    DoubleQuotes
    0.65
    Autoritní
    0.64
    expandindo
    0.64
    extAlignment
    0.62
    Vidite
    0.61
    Act Density 0.008%

    No Known Activations