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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and file path indicators

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

    documentation tags and code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Spitzen
    -0.33
    beispiel
    -0.33
    again
    -0.32
     Khusus
    -0.31
    expect
    -0.31
     esfor
    -0.30
    harapkan
    -0.29
    react
    -0.28
    delig
    -0.28
    sólo
    -0.28
    POSITIVE LOGITS
     GenerationType
    0.77
    EDEFAULT
    0.71
    WithIOException
    0.70
    :✨
    0.69
    principalColumn
    0.67
     snippetHide
    0.67
    UnusedPrivate
    0.65
    ⓧ
    0.65
    XmlAccessType
    0.64
    BufferException
    0.63
    Act Density 0.001%

    No Known Activations