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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    benef
    -0.06
     페
    -0.06
    ="/"
    -0.06
    monitor
    -0.06
     scanf
    -0.06
     созда
    -0.06
    >d
    -0.06
     Ere
    -0.06
     εξ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    >');↵
    0.07
    :";
↵
    0.07
     petty
    0.06
     Gang
    0.06
    خانه
    0.06
    ～↵↵
    0.06
     '))↵
    0.06
    /bash
    0.06
    ']↵
    0.06
     ambush
    0.06
    Act Density 0.003%

    No Known Activations