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

    Neuronpedia

    INDEX
    Explanations

    King Size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fine
    0.88
    kbd
    0.77
    queries
    0.76
    फाइन
    0.74
    FindBy
    0.74
    Browse
    0.73
    iquity
    0.70
    ૩
    0.70
    Find
    0.69
     unpack
    0.69
    POSITIVE LOGITS
     Temper
    0.75
     Cooperation
    0.74
     Consent
    0.74
     états
    0.74
     ஏற்படுகிறது
    0.73
     authorizing
    0.72
     Master
    0.72
    綸
    0.70
     aft
    0.69
     النوع
    0.69
    Act Density 0.000%

    No Known Activations