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

    Neuronpedia

    INDEX
    Explanations

    introducing clauses after when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ına
    0.96
     Belediyesi
    0.84
    ﮢ
    0.84
     Mathf
    0.83
    ʛ
    0.82
     protr
    0.80
     تكونوا
    0.80
    ار
    0.80
     phenytoin
    0.80
     sows
    0.79
    POSITIVE LOGITS
    р
    0.80
    bij
    0.67
    it
    0.66
    il
    0.65
    rad
    0.64
    r
    0.63
    n
    0.61
    p
    0.57
    нодоро
    0.56
    itra
    0.54
    Act Density 0.001%

    No Known Activations