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

    Neuronpedia

    INDEX
    Explanations

    twists and turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Smart
    0.60
     Aztecs
    0.59
     Beach
    0.57
    ur
    0.57
     Hague
    0.56
     री
    0.56
     Benefits
    0.56
    ंखला
    0.55
     Basis
    0.55
     Beer
    0.55
    POSITIVE LOGITS
     inesper
    0.74
     unforeseen
    0.73
     моего
    0.68
    r
    0.65
     différents
    0.64
     twists
    0.61
     changement
    0.61
     неожидан
    0.61
     моих
    0.61
     extremo
    0.60
    Act Density 0.036%

    No Known Activations