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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    a
    -0.09
    an
    -0.08
    A
    -0.08
     ETA
    -0.08
     Uma
    -0.07
     IRequest
    -0.07
    /A
    -0.07
    al
    -0.07
     McA
    -0.07
    ınca
    -0.07
    POSITIVE LOGITS
     agile
    0.07
    LV
    0.07
     Barbie
    0.07
     cassette
    0.06
    directories
    0.06
    рош
    0.06
    apor
    0.06
    lic
    0.06
    _ROLE
    0.06
    appropri
    0.06
    Act Density 0.221%

    No Known Activations