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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     और
    0.46
     και
    0.45
     ಮತ್ತು
    0.43
     અને
    0.43
     Và
    0.42
     এবং
    0.42
     ਅਤੇ
    0.42
     và
    0.41
     καὶ
    0.39
     आणि
    0.39
    POSITIVE LOGITS
     its
    2.48
     Its
    2.05
    Its
    2.05
    its
    1.79
    其
    1.69
    它的
    1.63
     அதன்
    1.60
     അതിന്റെ
    1.52
     其
    1.49
     उसके
    1.35
    Act Density 0.011%

    No Known Activations