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

    Neuronpedia

    INDEX
    Explanations

    falling in love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    써
    1.17
    kJ
    1.03
     for
    1.02
    े
    0.99
    ка
    0.97
    $,
    0.97
    ेड
    0.96
    confirmed
    0.96
    ности
    0.95
    ﯼ
    0.95
    POSITIVE LOGITS
    ad
    0.97
    0.82
    व
    0.78
    し
    0.78
     SALT
    0.77
     aérea
    0.77
    ير
    0.77
     a
    0.76
     OSU
    0.75
     FOREST
    0.74
    Act Density 0.008%

    No Known Activations