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

    Neuronpedia

    INDEX
    Explanations

    moss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rome
    0.84
    EEN
    0.84
    씬
    0.84
     Spectra
    0.84
     Akira
    0.82
     Boltzmann
    0.82
     Factor
    0.81
     Guant
    0.81
     Osama
    0.80
    avin
    0.80
    POSITIVE LOGITS
    م
    1.16
    ри
    1.03
    ર
    0.97
    м
    0.93
     pertes
    0.92
    ك
    0.90
    ة
    0.89
    िक
    0.88
    ون
    0.88
    υ
    0.87
    Act Density 0.001%

    No Known Activations