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

    Neuronpedia

    INDEX
    Explanations

    counterfeit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %↵↵
    -0.07
    -prepend
    -0.07
     Trek
    -0.06
    ....↵↵
    -0.06
    灌
    -0.06
    _experiment
    -0.06
     순
    -0.06
    振兴
    -0.06
    _hom
    -0.06
     Ult
    -0.06
    POSITIVE LOGITS
    Direct
    0.08
    _PARAMETER
    0.07
    odium
    0.07
    0.07
     tableName
    0.07
    RequestBody
    0.07
    ills
    0.07
    把控
    0.07
    笑容
    0.07
    amerate
    0.07
    Act Density 0.002%

    No Known Activations