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

    Neuronpedia

    INDEX
    Explanations

    hex codes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     меж
    0.67
    0.67
     infinitesimal
    0.63
     explicado
    0.60
     Scientology
    0.60
     hyvin
    0.59
     fruto
    0.59
     intercultural
    0.58
     Xs
    0.58
     وړاندوینه
    0.58
    POSITIVE LOGITS
    db
    1.06
    FF
    1.06
    bb
    1.02
    BB
    1.01
    AB
    1.00
    bc
    1.00
    dda
    1.00
    ff
    0.98
    abb
    0.98
    ba
    0.97
    Act Density 0.073%

    No Known Activations