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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autofocus
    -0.07
    =y
    -0.06
     Governor
    -0.06
    (generator
    -0.06
    _return
    -0.06
     motivation
    -0.06
     vrou
    -0.06
     Reader
    -0.06
     Covenant
    -0.06
    (return
    -0.06
    POSITIVE LOGITS
     соответствии
    0.07
    ']>;↵
    0.07
    년에는
    0.07
    لیت
    0.07
    '];↵
    0.07
    ');↵↵
    0.07
    ");↵↵
    0.07
    "]
↵
    0.07
    ])):↵
    0.07
     }])↵
    0.07
    Act Density 0.025%

    No Known Activations