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

    Neuronpedia

    INDEX
    Explanations

    assumptions after reasonable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.48
     Humphreys
    0.48
    ровой
    0.48
    rico
    0.47
    Mechan
    0.46
    rowth
    0.45
    Regional
    0.44
     Monique
    0.44
    h
    0.44
    Mod
    0.44
    POSITIVE LOGITS
     አለ
    0.47
    ்கலை
    0.46
    ıma
    0.45
    usahaan
    0.45
    ịa
    0.44
    话说
    0.44
     Correspondence
    0.44
    ");
    0.44
    "};
    0.44
     સર
    0.43
    Act Density 0.001%

    No Known Activations