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

    Neuronpedia

    INDEX
    Explanations

    return x, to produce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oomla
    0.69
     Pasta
    0.69
    รอง
    0.69
     verità
    0.69
     úlo
    0.68
    Formatted
    0.65
    寡
    0.65
    ัฒ
    0.65
    Pasta
    0.64
    ॉग
    0.63
    POSITIVE LOGITS
     equate
    0.77
    횟
    0.76
    时间
    0.75
     possessions
    0.75
     मामले
    0.75
    わざ
    0.73
    目标
    0.73
     replicate
    0.73
     alive
    0.73
     வைத்த
    0.73
    Act Density 0.000%

    No Known Activations