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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ステム
    -0.07
    ional
    -0.07
     varchar
    -0.07
    �ん
    -0.06
    ocs
    -0.06
    يين
    -0.06
    dp
    -0.06
    عار
    -0.06
    _BOOT
    -0.06
    ">{{
    -0.06
    POSITIVE LOGITS
     scares
    0.07
     perv
    0.07
     espan
    0.06
     destructive
    0.06
     photographed
    0.06
     penetrated
    0.06
     tied
    0.06
     Solomon
    0.06
     favourites
    0.06
     penetrate
    0.06
    Act Density 0.040%

    No Known Activations