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

    Neuronpedia

    INDEX
    Explanations

    preferred

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flink
    -0.08
     lapho
    -0.08
     ebb
    -0.08
     erl
    -0.08
     fash
    -0.07
     bất
    -0.07
    色
    -0.07
     jamais
    -0.07
    eprom
    -0.07
     jira
    -0.07
    POSITIVE LOGITS
    erweise
    0.09
     vivement
    0.09
     recommandé
    0.08
     discouraged
    0.08
     fortement
    0.08
     voire
    0.08
    [X
    0.08
     ఉంటుంది
    0.08
    recommended
    0.08
     الأحيان
    0.08
    Act Density 0.032%

    No Known Activations