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

    Neuronpedia

    INDEX
    Explanations

    believe followed by opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тка
    1.79
    ل
    1.63
    нка
    1.56
    selves
    1.52
    зва
    1.48
    ן
    1.46
    す
    1.45
    нкт
    1.41
    م
    1.40
    ﻑ
    1.39
    POSITIVE LOGITS
    it
    2.25
    㐄
    1.65
    ate
    1.63
    am
    1.58
    டன்
    1.58
    ic
    1.57
    এবং
    1.47
    ט
    1.47
    畔
    1.47
    ことにより
    1.46
    Act Density 0.010%

    No Known Activations