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

    Neuronpedia

    INDEX
    Explanations

    You

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forecasting
    -0.07
     meas
    -0.07
    .offer
    -0.07
     pawn
    -0.06
    寄
    -0.06
     simplify
    -0.06
     cudd
    -0.06
    금
    -0.06
    __/
    -0.06
     Mikhail
    -0.06
    POSITIVE LOGITS
    _K
    0.07
    팅
    0.07
     Sho
    0.07
    .source
    0.06
     ```
    0.06
    CREASE
    0.06
    ダ
    0.06
    _WM
    0.06
     mag
    0.06
    aseline
    0.06
    Act Density 0.011%

    No Known Activations