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

    Neuronpedia

    INDEX
    Explanations

    responsibilities, skills, and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essays
    0.48
     Physical
    0.46
    <h2>
    0.46
     Scientific
    0.46
     pedagogy
    0.46
     Cancer
    0.45
     Phenomen
    0.44
     psychology
    0.44
    self
    0.44
    teach
    0.43
    POSITIVE LOGITS
    ميم
    0.48
    ovala
    0.48
    كي
    0.48
    ərbay
    0.45
     זו
    0.44
    ాన్
    0.43
    zí
    0.43
    тити
    0.43
    ти
    0.43
    нах
    0.43
    Act Density 0.007%

    No Known Activations