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

    Neuronpedia

    INDEX
    Explanations

    potentially, yes, but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻝ
    1.02
    ﻭ
    0.94
    ruby
    0.93
    },
    0.92
    例えば
    0.89
    ﮈ
    0.88
    ക്കളുടെ
    0.88
    ﺎ
    0.88
    其
    0.86
    それは
    0.85
    POSITIVE LOGITS
    TO
    0.95
    v
    0.87
    ר
    0.85
    britannien
    0.84
     этап
    0.80
     Übers
    0.79
    িং
    0.79
     миллионов
    0.78
    ногда
    0.77
    دون
    0.77
    Act Density 0.000%

    No Known Activations