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

    Neuronpedia

    INDEX
    Explanations

    Elys Gauthier Lloyd Khan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.85
     tumble
    0.82
     angelic
    0.82
    نون
    0.81
    󠁴
    0.79
     migliore
    0.77
     ull
    0.76
    тоў
    0.76
     barbarian
    0.75
     hinzufügen
    0.75
    POSITIVE LOGITS
    }
    1.03
    },
    0.98
    Cinema
    0.93
    Patients
    0.93
    Ti
    0.91
    豸
    0.91
    L
    0.90
     मगर
    0.89
    Р
    0.88
    Sa
    0.88
    Act Density 0.070%

    No Known Activations