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

    Neuronpedia

    INDEX
    Explanations

    exam preparation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.97
    м
    1.96
    ある
    1.95
    ive
    1.92
    り
    1.82
    hood
    1.77
    odore
    1.74
    ticker
    1.73
    ો
    1.73
    ories
    1.70
    POSITIVE LOGITS
    টর
    2.31
    ش
    1.92
     exams
    1.87
    rustic
    1.87
    ER
    1.86
    EDY
    1.85
     lotions
    1.82
     methotrexate
    1.82
    ਢ
    1.82
    IED
    1.81
    Act Density 0.007%

    No Known Activations