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

    Neuronpedia

    INDEX
    Explanations

    lists, code, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     banter
    0.49
     EARL
    0.46
     mortality
    0.44
     scrambling
    0.44
     East
    0.43
    ,
    0.43
     sexual
    0.43
     Godwin
    0.43
    スト
    0.42
     tumbling
    0.42
    POSITIVE LOGITS
    وسیع
    0.41
    ুরী
    0.40
    Guj
    0.40
    TabData
    0.40
     (%
    0.40
    manager
    0.40
    fø
    0.40
    penup
    0.39
    acchati
    0.39
     regler
    0.39
    Act Density 0.000%

    No Known Activations