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

    Neuronpedia

    INDEX
    Explanations

    Computational Equivalence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     swoop
    0.39
    říve
    0.38
     nel
    0.38
     flared
    0.37
    Nel
    0.37
     chin
    0.36
     handle
    0.36
    აკ
    0.36
     veer
    0.36
     fazer
    0.36
    POSITIVE LOGITS
     epidemiological
    0.45
     Epidemi
    0.44
     Biological
    0.41
     Enough
    0.41
     epidemiology
    0.41
    Clinical
    0.41
     চন্দ্র
    0.40
    िखित
    0.40
     Uninstall
    0.40
     Ethical
    0.39
    Act Density 0.007%

    No Known Activations