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

    Neuronpedia

    INDEX
    Explanations

    I + action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluation
    0.81
    Previews
    0.78
     evaluation
    0.77
    Evaluation
    0.76
    evaluation
    0.74
    交付
    0.73
    形式
    0.71
    Debt
    0.70
     زبان
    0.69
     trao
    0.69
    POSITIVE LOGITS
     ignore
    0.90
    注目
    0.82
     Ignore
    0.82
     ignores
    0.81
     ignored
    0.81
     attribute
    0.79
     caul
    0.77
     antihist
    0.77
     nume
    0.77
     swat
    0.77
    Act Density 0.104%

    No Known Activations