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

    Neuronpedia

    INDEX
    Explanations

    needing any advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Db
    -0.07
    _GROUPS
    -0.07
     jugg
    -0.07
     gefunden
    -0.06
     Keep
    -0.06
    anda
    -0.06
     반환
    -0.06
     dicho
    -0.06
    _zip
    -0.06
    とも
    -0.06
    POSITIVE LOGITS
     reproduce
    0.07
     Sophie
    0.07
     mouseY
    0.06
     Jessie
    0.06
     Monterey
    0.06
     SAR
    0.06
     collapse
    0.06
    Gl
    0.06
    .HashSet
    0.06
     WWII
    0.06
    Act Density 0.171%

    No Known Activations