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

    Neuronpedia

    INDEX
    Explanations

    effectiveness, adding, high frequencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    以下
    0.76
     Ciencias
    0.76
    지난
    0.76
    تش
    0.75
    Linux
    0.74
    𝙄
    0.73
    寯
    0.72
    哴
    0.71
     comisión
    0.70
    라면
    0.70
    POSITIVE LOGITS
     sukces
    0.71
    orbid
    0.69
    ں
    0.68
     menyelesaikan
    0.66
     הס
    0.66
     বিস্ফোর
    0.64
     standoff
    0.63
     sweetener
    0.62
     seized
    0.61
     surviving
    0.61
    Act Density 0.000%

    No Known Activations