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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UTC
    -0.06
    �
    -0.06
    讯
    -0.06
    豊
    -0.06
    лиц
    -0.06
    >C
    -0.06
    일본
    -0.06
     موبایل
    -0.06
    اشین
    -0.06
    /Test
    -0.06
    POSITIVE LOGITS
     Called
    0.07
     NEVER
    0.07
    _ALWAYS
    0.06
    -comment
    0.06
     моря
    0.06
    abler
    0.06
     없는
    0.06
    tro
    0.06
    ização
    0.06
    _Matrix
    0.06
    Act Density 0.246%

    No Known Activations