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

    Neuronpedia

    INDEX
    Explanations

    utilitarianism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presiding
    0.46
     fragmentary
    0.46
     Nguyên
    0.45
    aguars
    0.44
     consecut
    0.43
     toured
    0.42
    OFF
    0.42
     febbraio
    0.42
     制
    0.42
    case
    0.41
    POSITIVE LOGITS
    })}{\
    0.57
    Гц
    0.53
     wavelengths
    0.46
    тири
    0.44
    Regex
    0.44
    مپ
    0.44
    ExprNode
    0.44
     врач
    0.43
    ਨ
    0.43
    Downloading
    0.43
    Act Density 0.003%

    No Known Activations