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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fputs
    -0.08
    扎
    -0.07
    dol
    -0.06
    Touches
    -0.06
    .*;↵↵
    -0.06
    '];?>"
    -0.06
    enth
    -0.06
    ?:
    -0.06
    دهم
    -0.06
     procedures
    -0.06
    POSITIVE LOGITS
    lerimiz
    0.06
    ически
    0.06
     British
    0.06
     UM
    0.06
    "http
    0.06
    |
    0.06
    Florida
    0.06
    .Back
    0.06
    Logic
    0.06
    http
    0.06
    Act Density 0.046%

    No Known Activations