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

    Neuronpedia

    INDEX
    Explanations

    Politico and Project Gutenberg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.63
     എടു
    0.63
    자와
    0.61
    滗
    0.61
     восстановления
    0.60
    માં
    0.59
    in
    0.59
     Graeme
    0.59
    VOL
    0.58
    t
    0.58
    POSITIVE LOGITS
     of
    0.88
    fice
    0.61
     can
    0.59
     vidrio
    0.56
    ;
    0.56
    elier
    0.55
     quirks
    0.55
     l
    0.55
     variedad
    0.55
    cnico
    0.55
    Act Density 0.000%

    No Known Activations