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

    Neuronpedia

    INDEX
    Explanations

    business and technical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.49
     an
    0.43
     of
    0.40
     these
    0.40
     a
    0.40
     all
    0.39
     this
    0.37
     are
    0.36
     two
    0.36
     network
    0.36
    POSITIVE LOGITS
    ЕР
    0.41
    לי
    0.40
    ר
    0.39
     או
    0.38
    ש
    0.38
    Existe
    0.37
    युद्ध
    0.37
    בי
    0.36
    КА
    0.36
    רו
    0.36
    Act Density 0.272%

    No Known Activations