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

    Neuronpedia

    INDEX
    Explanations

    CTA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tests
    -0.44
    ah
    -0.44
    less
    -0.43
    こ
    -0.41
    ने
    -0.41
     olev
    -0.41
    lendir
    -0.41
     Mejor
    -0.40
     Melhor
    -0.40
    ть
    -0.40
    POSITIVE LOGITS
     صوتيه
    0.79
    ConstraintMaker
    0.73
    IVEREF
    0.73
     dAtA
    0.72
    RegistryLite
    0.72
     للاسماء
    0.67
    IndentedString
    0.67
     GenerationType
    0.66
     EnglishChoose
    0.66
    contentLoaded
    0.65
    Act Density 0.000%

    No Known Activations