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

    Neuronpedia

    INDEX
    Explanations

    compiled, acquainted, all, items, hits, string, marking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     review
    0.74
    iment
    0.68
     Prohibition
    0.67
     personally
    0.66
     enforcement
    0.65
     Review
    0.65
     enforceable
    0.62
     reviewing
    0.61
     reassurance
    0.61
     unreported
    0.60
    POSITIVE LOGITS
    By
    0.89
    渽
    0.88
    綎
    0.88
     этими
    0.87
     таким
    0.86
     глаз
    0.85
    盽
    0.84
    ependent
    0.84
     вами
    0.83
    reh
    0.83
    Act Density 0.000%

    No Known Activations