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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elp
    -0.07
    olith
    -0.07
    �
    -0.07
    ुज
    -0.07
    instancetype
    -0.06
    graf
    -0.06
     돈
    -0.06
    mailer
    -0.06
     farmhouse
    -0.06
    lung
    -0.06
    POSITIVE LOGITS
    SetTitle
    0.07
    assertTrue
    0.06
        ↵↵
    0.06
    .acc
    0.06
     druhé
    0.06
     belki
    0.06
     smě
    0.06
     pipes
    0.06
    建议
    0.06
     گونه
    0.06
    Act Density 0.002%

    No Known Activations