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

    Neuronpedia

    INDEX
    Explanations

    encoding error character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Virt
    -0.06
     Kraj
    -0.06
     tổng
    -0.06
     Çev
    -0.06
     anchor
    -0.06
     tracing
    -0.06
     grounded
    -0.06
    .cap
    -0.06
    teacher
    -0.06
     Hamp
    -0.06
    POSITIVE LOGITS
    ::_
    0.07
    ela
    0.07
     punctuation
    0.07
     Gi�
    0.07
    (Un
    0.06
    :h
    0.06
    ensa
    0.06
    :E
    0.06
    ":[-
    0.06
    /_
    0.06
    Act Density 0.007%

    No Known Activations