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

    Neuronpedia

    INDEX
    Explanations

    lists of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifikation
    0.50
    ika
    0.48
    format
    0.48
    igo
    0.47
    ä
    0.47
    ë
    0.46
    ushima
    0.46
    esthesia
    0.46
    addie
    0.45
    igg
    0.44
    POSITIVE LOGITS
    OrCreate
    0.47
    帥
    0.47
    ရေး
    0.46
     کسب
    0.45
    Charting
    0.45
    还能
    0.45
    ית
    0.44
    StudentRecord
    0.44
    مين
    0.43
     Calhoun
    0.42
    Act Density 0.000%

    No Known Activations