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

    Neuronpedia

    INDEX
    Explanations

    technical mathematical terms and symbols

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

    Citation or reference markers

    np_acts-logits-general · gemini-2.0-flash

    code related to versions and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.65
    OGND
    -0.64
    AlterField
    -0.63
    memoized
    -0.60
     ويكيپيديا
    -0.60
    مصادر
    -0.60
    OPHER
    -0.59
    。</
    -0.59
     Numerade
    -0.57
    ApiModelProperty
    -0.57
    POSITIVE LOGITS
    .
    1.37
    TestingModule
    0.58
    ٫
    0.52
     GenerationType
    0.50
    /**
    0.49
    ReusableCell
    0.48
    ½
    0.45
     createState
    0.44
    .*,
    0.44
    ("")]
    0.41
    Act Density 1.650%

    No Known Activations