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

    Neuronpedia

    INDEX
    Explanations

    it's important to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நான்கு
    0.54
     indispensables
    0.54
     сколько
    0.52
    は
    0.51
     número
    0.50
    是
    0.50
     क्रमांका
    0.49
     devem
    0.48
    는
    0.48
    あらゆる
    0.48
    POSITIVE LOGITS
    t
    0.77
    a
    0.58
    ir
    0.57
     we
    0.56
    r
    0.53
     I
    0.50
    f
    0.50
    ad
    0.48
    g
    0.48
     We
    0.47
    Act Density 0.022%

    No Known Activations