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

    Neuronpedia

    INDEX
    Explanations

    know what/how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kidnapping
    0.82
     recalc
    0.78
    as
    0.75
     revolution
    0.75
    ension
    0.74
     vigilance
    0.73
    etition
    0.73
     There
    0.72
    ется
    0.72
     graphing
    0.72
    POSITIVE LOGITS
    Какие
    0.92
    WHAT
    0.91
    कौन
    0.88
    是什麼
    0.84
    arrêter
    0.84
    Apakah
    0.83
     hvil
    0.82
     hvordan
    0.82
    什么是
    0.80
    Whether
    0.80
    Act Density 0.100%

    No Known Activations