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

    Neuronpedia

    INDEX
    Explanations

    explanation: code documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XPath
    0.97
    searchValue
    0.96
     bons
    0.91
     sympy
    0.89
    dplyr
    0.89
    }$.,
    0.87
     dysplasia
    0.86
     अंकों
    0.85
     matemáticas
    0.85
     eigenvalue
    0.84
    POSITIVE LOGITS
    ból
    0.88
    Į
    0.85
    אות
    0.84
    ير
    0.81
    目的
    0.79
    tedir
    0.79
    тири
    0.78
    Ԁ
    0.78
    wała
    0.78
    uing
    0.77
    Act Density 0.019%

    No Known Activations