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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DJ
    -0.07
     뛰
    -0.06
    -trade
    -0.06
     rap
    -0.06
     absorption
    -0.06
    \":
    -0.06
     genus
    -0.06
    死
    -0.06
     Pal
    -0.06
     HPV
    -0.06
    POSITIVE LOGITS
    ayız
    0.06
     Blood
    0.06
     wrongly
    0.06
    ifik
    0.06
    czas
    0.06
    며
    0.06
    .Toolbar
    0.06
    يو
    0.06
    _Last
    0.06
     fikir
    0.06
    Act Density 0.043%

    No Known Activations