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

    Neuronpedia

    INDEX
    Explanations

    ices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .InputStream
    -0.07
     cold
    -0.07
     захисту
    -0.07
    ��
    -0.06
    lead
    -0.06
     Bac
    -0.06
     WL
    -0.06
    Este
    -0.06
     Credit
    -0.06
    ockets
    -0.06
    POSITIVE LOGITS
     ¥
    0.06
     가정
    0.06
    .osgi
    0.06
     FullName
    0.06
     fotoğraf
    0.06
     abusing
    0.06
    ث
    0.06
     lokale
    0.06
    lásil
    0.06
    actual
    0.06
    Act Density 0.000%

    No Known Activations