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

    Neuronpedia

    INDEX
    Explanations

    Math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ಗಂಟ
    -0.08
     driver
    -0.08
     గంట
    -0.08
    \Common
    -0.08
     hours
    -0.08
    ediator
    -0.08
    จำนวน
    -0.07
     timmar
    -0.07
     horas
    -0.07
     午
    -0.07
    POSITIVE LOGITS
     negligible
    0.08
     neglig
    0.08
    MOST
    0.08
     abst
    0.08
     diminish
    0.08
    _suffix
    0.07
     resurgence
    0.07
    png
    0.07
    dismiss
    0.07
    practice
    0.07
    Act Density 0.012%

    No Known Activations