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

    Neuronpedia

    INDEX
    Explanations

    you will be logged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉత్ప
    0.40
    یکن
    0.40
    volved
    0.38
     했다
    0.38
    یکی
    0.37
     startup
    0.37
     one
    0.36
     manifested
    0.36
     했습니다
    0.36
    RIBUT
    0.35
    POSITIVE LOGITS
     humides
    0.46
     zobac
    0.44
     ruhig
    0.44
     обеспечивает
    0.42
    नि
    0.41
     prochains
    0.41
     decisiones
    0.40
     apenas
    0.40
     adicionales
    0.40
    Graham
    0.40
    Act Density 0.000%

    No Known Activations