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

    Neuronpedia

    INDEX
    Explanations

    80/20 rule

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sciences
    -0.07
     progress
    -0.07
     proving
    -0.07
     century
    -0.06
     ça
    -0.06
     face
    -0.06
     Examples
    -0.06
    )%
    -0.06
     remain
    -0.06
     Irvine
    -0.06
    POSITIVE LOGITS
     เจ
    0.07
    hcp
    0.07
    είς
    0.07
    _streams
    0.06
    _guide
    0.06
    .decoder
    0.06
    λά
    0.06
     TLS
    0.06
    clado
    0.06
    pay
    0.06
    Act Density 0.005%

    No Known Activations