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

    Neuronpedia

    INDEX
    Explanations

    technical and programming-related terminology

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

    The token "common" followed by various characters

    np_acts-logits-general · gemini-2.0-flash

    common prefixes and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.66
    andExpect
    -0.63
    principalColumn
    -0.60
    ParallelGroup
    -0.59
    ंदीखरीदारी
    -0.56
     مرئيه
    -0.55
     nahilalakip
    -0.55
    IntoConstraints
    -0.54
    adpleegd
    -0.50
     ब्रेकडाउन
    -0.50
    POSITIVE LOGITS
    common
    0.51
    COMMON
    0.50
    CommonModule
    0.50
     algemene
    0.48
    generic
    0.44
     shared
    0.43
    shared
    0.43
     common
    0.42
     generales
    0.42
    Common
    0.41
    Act Density 0.210%

    No Known Activations