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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /foo
    -0.06
     pá
    -0.06
    율
    -0.06
    [#
    -0.06
    }`,↵
    -0.06
    (fp
    -0.06
    )),↵
    -0.06
     triple
    -0.06
    amin
    -0.06
     cJSON
    -0.06
    POSITIVE LOGITS
    macros
    0.07
    .Failure
    0.07
     bites
    0.06
    教授
    0.06
    _Width
    0.06
    基地
    0.06
     situace
    0.06
     statistically
    0.06
     نتیجه
    0.06
     advertisers
    0.06
    Act Density 0.029%

    No Known Activations