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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tinder
    -0.06
     Gross
    -0.06
     чтобы
    -0.06
     week
    -0.06
    'an
    -0.06
    окон
    -0.06
    afa
    -0.06
     	↵
    -0.05
     sit
    -0.05
     visited
    -0.05
    POSITIVE LOGITS
    obuf
    0.07
     keycode
    0.07
     SSA
    0.07
    InOut
    0.07
    ��
    0.07
    .sym
    0.07
    .ex
    0.07
    /business
    0.06
     descriptors
    0.06
    -create
    0.06
    Act Density 0.000%

    No Known Activations