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

    Neuronpedia

    INDEX
    Explanations

    RCS descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.49
    ")
    0.46
    ered
    0.43
    ED
    0.43
    King
    0.42
    "));
    0.41
    ular
    0.41
    king
    0.40
    X
    0.40
    Sol
    0.39
    POSITIVE LOGITS
     marki
    0.64
     categorias
    0.55
     precession
    0.52
     userId
    0.52
     exce
    0.52
     variational
    0.50
     génération
    0.50
     emulator
    0.49
     vati
    0.48
     FUEL
    0.48
    Act Density 0.002%

    No Known Activations