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

    Neuronpedia

    INDEX
    Explanations

    alignment, horror, tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]");
    0.42
    }");
    0.41
    viewDidLoad
    0.39
    abet
    0.37
    artig
    0.36
    }]},
    0.36
     interv
    0.35
    梶
    0.35
     कार्
    0.35
    automat
    0.35
    POSITIVE LOGITS
    ෙහි
    0.40
     FLOAT
    0.39
     cone
    0.39
    徂
    0.38
     සං
    0.38
     excel
    0.37
     गरेको
    0.37
     taking
    0.36
    ర్
    0.36
     পৃষ্ঠা
    0.36
    Act Density 0.000%

    No Known Activations