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

    Neuronpedia

    INDEX
    Explanations

    for those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হইয়৷
    0.28
     klasik
    0.28
     anggaran
    0.28
     STARTED
    0.27
     แต่
    0.26
     MARTIN
    0.26
    URATION
    0.26
     gluon
    0.26
     ALLEN
    0.25
    ру
    0.25
    POSITIVE LOGITS
    O
    0.31
    F
    0.30
    L
    0.29
    W
    0.29
    J
    0.26
    H
    0.26
    I
    0.26
    IS
    0.25
    E
    0.24
    본
    0.24
    Act Density 0.000%

    No Known Activations