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

    Neuronpedia

    INDEX
    Explanations

    too

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubre
    -0.08
    -0.07
     Opportunity
    -0.07
     translations
    -0.06
    ollapse
    -0.06
     center
    -0.06
    _assignment
    -0.06
    Injected
    -0.06
     breastfeeding
    -0.06
     resisted
    -0.06
    POSITIVE LOGITS
     apparel
    0.07
    /map
    0.06
    کرد
    0.06
    -hero
    0.06
    040
    0.06
     คณะ
    0.06
     Vu
    0.06
    /pg
    0.06
    とう
    0.06
     Fedora
    0.06
    Act Density 0.027%

    No Known Activations