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

    Neuronpedia

    INDEX
    Explanations

    words related to the math, computation and coding.

    oai_token-act-pair · gemini-2.0-flash

    bits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cdef
    -0.48
    ISODE
    -0.47
    maic
    -0.45
    findpost
    -0.45
    paramInt
    -0.43
    ENTON
    -0.43
     Monti
    -0.43
    AndEndTag
    -0.42
    nologies
    -0.41
    неопр
    -0.41
    POSITIVE LOGITS
     bit
    0.96
    bit
    0.88
     Bit
    0.80
     bits
    0.77
    Bit
    0.75
     Bits
    0.70
    bits
    0.69
     Roskov
    0.67
    migrationBuilder
    0.67
     مشين
    0.65
    Act Density 3.556%

    No Known Activations