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

    Neuronpedia

    INDEX
    Explanations

    agreement/willingness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ultrap
    -0.10
     aufreg
    -0.08
     spikes
    -0.08
     élevé
    -0.08
     Configuration
    -0.08
     Elevated
    -0.08
     sinn
    -0.08
     Shall
    -0.07
     Disable
    -0.07
     elegante
    -0.07
    POSITIVE LOGITS
    愿
    0.11
     willingness
    0.11
     willingly
    0.09
    回应
    0.08
    认可
    0.08
    支持
    0.08
    awanda
    0.08
     goodwill
    0.08
     willing
    0.08
     grud
    0.08
    Act Density 0.187%

    No Known Activations