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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bracelets
    -0.07
    حل
    -0.06
    compression
    -0.06
    Flow
    -0.06
    _sup
    -0.06
     mínimo
    -0.06
     frais
    -0.06
    ラック
    -0.06
    -stage
    -0.06
     github
    -0.06
    POSITIVE LOGITS
    :")
    0.07
     Serbia
    0.07
     anarch
    0.07
     poru
    0.07
     webhook
    0.06
     _$
    0.06
     distra
    0.06
     Scientific
    0.06
    ooth
    0.06
    ough
    0.06
    Act Density 0.008%

    No Known Activations