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

    Neuronpedia

    INDEX
    Explanations

    options and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guidance
    0.48
    GUID
    0.45
     Guidance
    0.45
    guid
    0.43
     hand
    0.42
     hugged
    0.42
    Guid
    0.42
     longitudinal
    0.42
     Guid
    0.42
     whispering
    0.41
    POSITIVE LOGITS
     değer
    0.46
    っぱり
    0.46
    qquad
    0.44
     democracia
    0.44
    Docket
    0.43
     অভ্যাস
    0.42
    values
    0.41
     Litigation
    0.41
     docket
    0.40
    норийска
    0.40
    Act Density 0.001%

    No Known Activations