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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ी-
    -0.07
     sayılı
    -0.07
    guest
    -0.07
     plut
    -0.06
    ude
    -0.06
     crimes
    -0.06
     bullied
    -0.06
     ngoài
    -0.06
     Stay
    -0.06
     réseau
    -0.06
    POSITIVE LOGITS
    Marco
    0.07
    '];?>"
    0.06
    ,map
    0.06
     or
    0.06
    wcsstore
    0.06
    .plot
    0.06
    OUNDS
    0.06
    ,R
    0.06
    ,↵↵↵↵
    0.06
    (":/
    0.06
    Act Density 0.031%

    No Known Activations