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

    Neuronpedia

    INDEX
    Explanations

    Ambiguous/broad phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    py
    -0.08
     கை
    -0.07
    anova
    -0.07
     contam
    -0.07
    utip
    -0.07
     Fak
    -0.07
     Hydra
    -0.07
     fotogra
    -0.07
     Chinatown
    -0.07
    .dispose
    -0.07
    POSITIVE LOGITS
     feminine
    0.09
     plural
    0.09
     insufficient
    0.08
     curiosity
    0.08
     noun
    0.08
     במש
    0.08
     व्यापक
    0.08
    響
    0.08
     khá
    0.08
     wording
    0.07
    Act Density 0.062%

    No Known Activations