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

    Neuronpedia

    INDEX
    Explanations

    cover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -loader
    -0.07
    found
    -0.07
    WAR
    -0.07
    ToJson
    -0.06
    .water
    -0.06
    (factory
    -0.06
     RADIO
    -0.06
     hazard
    -0.06
    umber
    -0.06
    osh
    -0.06
    POSITIVE LOGITS
    isers
    0.06
     Sexy
    0.06
     männer
    0.06
    Sexy
    0.06
     crowd
    0.06
     découvrir
    0.06
    ，可
    0.06
    ┬
    0.06
     @{
    0.06
    ें।↵
    0.06
    Act Density 0.002%

    No Known Activations