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

    Neuronpedia

    INDEX
    Explanations

    brackets and parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phase
    -0.07
    Dictionary
    -0.07
     vurgu
    -0.07
    ΑΣ
    -0.07
     Их
    -0.06
     Hệ
    -0.06
     expectedResult
    -0.06
     sır
    -0.06
    Lets
    -0.06
     ولد
    -0.06
    POSITIVE LOGITS
    (""))↵
    0.07
     diplomats
    0.06
     ofrec
    0.06
    opolitan
    0.06
    99
    0.06
    :UIControlStateNormal
    0.06
    }');↵
    0.06
     ""));↵
    0.06
    askell
    0.06
    tz
    0.06
    Act Density 0.007%

    No Known Activations