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

    Neuronpedia

    INDEX
    Explanations

    Translations and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sexo
    -0.07
     dag
    -0.07
    pData
    -0.07
     mujer
    -0.07
    드립니다
    -0.07
    เร
    -0.07
    ----------------------------------------------------------------
    -0.07
     interdisciplinary
    -0.07
     singular
    -0.07
    货物
    -0.06
    POSITIVE LOGITS
    工厂
    0.07
     EXPER
    0.07
     PROM
    0.07
    .CheckedChanged
    0.07
     Changed
    0.07
    _ATTRIBUTES
    0.07
     limit
    0.07
    效应
    0.06
     практи
    0.06
    팰
    0.06
    Act Density 0.081%

    No Known Activations