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

    Neuronpedia

    INDEX
    Explanations

    encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ANAL
    -0.07
     Proposition
    -0.06
     Rise
    -0.06
    бина
    -0.06
     undes
    -0.06
     يق
    -0.06
    pace
    -0.06
    ystack
    -0.06
    vl
    -0.06
    -inter
    -0.06
    POSITIVE LOGITS
     большин
    0.07
    ایل
    0.06
    سات
    0.06
     Georgian
    0.06
    .Normalize
    0.06
     Usuarios
    0.06
    amics
    0.06
    ......
    0.06
    させる
    0.06
     зрения
    0.06
    Act Density 0.000%

    No Known Activations