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

    Neuronpedia

    INDEX
    Explanations

    CPR/compressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ĭ
    -0.08
     Explorer
    -0.07
    SmartyHeaderCode
    -0.07
    -fired
    -0.07
    奥迪
    -0.07
    ONUS
    -0.07
     Wright
    -0.07
    傲
    -0.07
    商铺
    -0.07
    قيد
    -0.07
    POSITIVE LOGITS
    Maria
    0.07
    arden
    0.06
     gramm
    0.06
    _datas
    0.06
    arto
    0.06
    hausen
    0.06
    社会保障
    0.06
    —which
    0.06
    —are
    0.06
    ᆞ
    0.06
    Act Density 0.003%

    No Known Activations