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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沮丧
    -0.07
    ﴼ
    -0.07
    овое
    -0.07
    应该是
    -0.07
    uevo
    -0.07
     fame
    -0.07
    玫
    -0.07
    _Settings
    -0.07
    勍
    -0.07
     Metodo
    -0.07
    POSITIVE LOGITS
    against
    0.07
    TEMPL
    0.07
    _CELL
    0.07
    勤
    0.07
    เน
    0.06
    kt
    0.06
    株
    0.06
    既有
    0.06
     FAILURE
    0.06
    广州市
    0.06
    Act Density 0.002%

    No Known Activations