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

    Neuronpedia

    INDEX
    Explanations

    ..

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tumor
    -0.07
    iesel
    -0.07
     Champion
    -0.07
    народ
    -0.06
     weapons
    -0.06
    ropic
    -0.06
    身
    -0.06
    武器
    -0.06
     potatoes
    -0.06
    skins
    -0.06
    POSITIVE LOGITS
    -kind
    0.06
    /mat
    0.06
     AD
    0.06
     吉
    0.06
    \Request
    0.06
     ليس
    0.05
    plex
    0.05
    .xz
    0.05
     professionnel
    0.05
    :req
    0.05
    Act Density 0.001%

    No Known Activations