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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Just
    0.77
    Strong
    0.66
     Just
    0.65
     কখনো
    0.62
     сра
    0.61
     just
    0.60
    राल
    0.60
    Expert
    0.59
    Haven
    0.58
    rscheinlich
    0.58
    POSITIVE LOGITS
     only
    2.16
    only
    2.04
     Only
    1.97
     purposes
    1.91
    Only
    1.91
     seulement
    1.80
     ONLY
    1.75
    เท่านั้น
    1.73
    ONLY
    1.69
     فقط
    1.66
    Act Density 0.020%

    No Known Activations