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

    Neuronpedia

    INDEX
    Explanations

    code and file formats

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cancel
    0.68
    AST
    0.64
    িষ
    0.60
     Informed
    0.58
     informed
    0.57
     cancelar
    0.57
     honesty
    0.56
    лкой
    0.55
     shocked
    0.54
    Cancelar
    0.54
    POSITIVE LOGITS
     Pozn
    0.62
    wn
    0.56
     نگر
    0.55
    gios
    0.54
     ময়
    0.53
    діть
    0.53
    ماية
    0.52
    コク
    0.52
     panneaux
    0.52
    窒
    0.52
    Act Density 0.001%

    No Known Activations