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

    Neuronpedia

    INDEX
    Explanations

    impeccable, irritant, tolerant, resistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ografia
    0.89
    ación
    0.88
    ydd
    0.84
    ENA
    0.84
    aquin
    0.84
    oksi
    0.82
    olab
    0.82
     andolan
    0.82
    uidor
    0.81
    ência
    0.80
    POSITIVE LOGITS
     Cartesian
    0.76
    筁
    0.71
     Mell
    0.71
     HSBC
    0.69
    Life
    0.68
     Santa
    0.68
    Le
    0.67
     UML
    0.67
    Tooth
    0.67
     Hier
    0.66
    Act Density 0.002%

    No Known Activations