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

    Neuronpedia

    INDEX
    Explanations

    5xx errorsremove shoestruly shines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OMBRE
    0.52
     अत्यंत
    0.51
    ومه
    0.51
    驯
    0.51
    ."),
    0.51
     செய்வது
    0.50
    ದಲು
    0.48
    两侧
    0.48
     doubleheader
    0.47
     psychosocial
    0.47
    POSITIVE LOGITS
    dr
    0.50
    0.50
     Website
    0.47
    יי
    0.46
    ier
    0.44
    Website
    0.43
     Pat
    0.43
    ale
    0.41
    die
    0.41
     Im
    0.41
    Act Density 0.001%

    No Known Activations