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

    Neuronpedia

    INDEX
    Explanations

    code and website carousels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кап
    -0.07
     agli
    -0.07
     φω
    -0.06
    _rule
    -0.06
    .len
    -0.06
     состояния
    -0.06
    _CHANNEL
    -0.06
    ü
    -0.06
     بور
    -0.06
     Determines
    -0.06
    POSITIVE LOGITS
    意
    0.07
    _verified
    0.07
    detach
    0.06
     coraz
    0.06
     lm
    0.06
    brakk
    0.06
     NYC
    0.06
    těz
    0.06
    nivel
    0.06
    _Construct
    0.06
    Act Density 0.000%

    No Known Activations