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

    Neuronpedia

    INDEX
    Explanations

    required for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    といっても
    -0.08
     Celtic
    -0.07
    电子商务
    -0.07
    مغرب
    -0.07
    港股
    -0.07
    提早
    -0.07
    )prepareForSegue
    -0.07
    💱
    -0.06
     pharmac
    -0.06
    🥘
    -0.06
    POSITIVE LOGITS
    rez
    0.07
    Й
    0.07
    ry
    0.07
    씀
    0.07
    sf
    0.06
     wird
    0.06
     Att
    0.06
    _returns
    0.06
     resolves
    0.06
     care
    0.06
    Act Density 0.033%

    No Known Activations