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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <d
    -0.07
    accur
    -0.06
    acoes
    -0.06
    екотор
    -0.06
    numer
    -0.06
    ё
    -0.06
    rup
    -0.06
     kd
    -0.06
    Excel
    -0.06
    greso
    -0.06
    POSITIVE LOGITS
    toa
    0.06
    одар
    0.06
     unpredictable
    0.06
    하면서
    0.06
    ビ
    0.06
    ์↵↵
    0.06
     دشمن
    0.06
    먼
    0.06
     드라마
    0.06
     closet
    0.06
    Act Density 0.085%

    No Known Activations