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

    Neuronpedia

    INDEX
    Explanations

    specific concepts and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uming
    0.38
    manufacturing
    0.37
     Balliye
    0.37
    जापुर
    0.36
    imantan
    0.36
    웡
    0.36
    activities
    0.36
    immune
    0.35
     політи
    0.35
     Political
    0.34
    POSITIVE LOGITS
     luch
    0.42
     perfection
    0.42
     comprehend
    0.41
     perfect
    0.40
     perfected
    0.39
    isl
    0.39
     pita
    0.38
    ্না
    0.38
    ্যার
    0.38
     insight
    0.38
    Act Density 0.000%

    No Known Activations