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

    Neuronpedia

    INDEX
    Explanations

    respectful relationship resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    2.14
    (""))
    1.52
    i
    1.52
    従って
    1.47
     kleiner
    1.45
    %).
    1.42
    ্লাহ
    1.36
     %).
    1.35
    $.
    1.34
    ați
    1.34
    POSITIVE LOGITS
     exacerb
    1.45
    सह
    1.44
    ază
    1.42
    habit
    1.42
     объем
    1.40
     motivo
    1.40
    ाय
    1.40
    auté
    1.39
    ции
    1.36
    ু
    1.35
    Act Density 0.002%

    No Known Activations