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

    Neuronpedia

    INDEX
    Explanations

    concise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     princess
    0.57
    щин
    0.55
     drank
    0.54
     graus
    0.54
     battlefield
    0.53
     grains
    0.53
    ಚಿತ
    0.52
    ारे
    0.52
     skewers
    0.52
    луй
    0.51
    POSITIVE LOGITS
    がある
    0.71
    調
    0.71
    不定
    0.69
     அக்க
    0.68
     દર
    0.66
     الدول
    0.63
    Acetyl
    0.63
    Cod
    0.63
    ポップ
    0.62
    avaju
    0.61
    Act Density 0.159%

    No Known Activations