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

    Neuronpedia

    INDEX
    Explanations

    Java code or acoustic waves

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     진
    -0.08
    .ZERO
    -0.07
    ⠒
    -0.07
    檐
    -0.07
    跐
    -0.07
    >Type
    -0.07
    ząd
    -0.07
     mười
    -0.07
    �
    -0.07
    겸
    -0.06
    POSITIVE LOGITS
    _embeddings
    0.07
     Publié
    0.07
     мужчин
    0.07
    Editors
    0.07
     host
    0.07
     weakest
    0.06
    Knight
    0.06
    кам
    0.06
     Roberts
    0.06
     Freedom
    0.06
    Act Density 0.000%

    No Known Activations