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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    핧
    -0.08
    _rho
    -0.07
    大きい
    -0.07
    Strategy
    -0.07
    Pattern
    -0.07
    铝
    -0.07
    </tool_call>
    -0.07
    不舒服
    -0.07
    磡
    -0.07
    ขยาย
    -0.06
    POSITIVE LOGITS
     Pvt
    0.08
     İç
    0.07
     Needless
    0.07
     ness
    0.07
    vely
    0.07
    OC
    0.07
     survival
    0.07
     Diğer
    0.06
     вс
    0.06
     outfield
    0.06
    Act Density 0.002%

    No Known Activations