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

    Neuronpedia

    INDEX
    Explanations

    swift guard statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.60
    els
    0.55
    si
    0.54
    rou
    0.54
    did
    0.51
    iorno
    0.51
    ώσει
    0.51
    لبية
    0.50
    pio
    0.50
    entliche
    0.50
    POSITIVE LOGITS
     hidrógeno
    0.66
     Uttar
    0.59
     کر
    0.58
     \[
    0.58
     crist
    0.57
    드의
    0.56
     tranqu
    0.55
     Idha
    0.55
     Yu
    0.55
     Phật
    0.55
    Act Density 0.000%

    No Known Activations