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

    Neuronpedia

    INDEX
    Explanations

    36

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,num
    -0.06
    Condition
    -0.06
    ------
    -0.06
    Again
    -0.06
     hashlib
    -0.06
    elapsed
    -0.06
    иц
    -0.06
    _version
    -0.06
     Dancing
    -0.06
    .goal
    -0.06
    POSITIVE LOGITS
    %=
    0.07
     ऋ
    0.06
    mandatory
    0.06
     ภาษ
    0.06
     torch
    0.06
     getP
    0.06
    lon
    0.06
    miştir
    0.06
    برد
    0.06
     дити
    0.06
    Act Density 0.000%

    No Known Activations