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

    Neuronpedia

    INDEX
    Explanations

    positive/negative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Validation
    -0.07
     Genome
    -0.07
     approved
    -0.06
     lines
    -0.06
    _Metadata
    -0.06
     boxes
    -0.06
    icient
    -0.06
     criteria
    -0.06
     Cho
    -0.06
     BaseController
    -0.06
    POSITIVE LOGITS
     =>
    0.07
    テレビ
    0.07
    _GUI
    0.06
     εισ
    0.06
     професій
    0.06
    ,exports
    0.06
     만나
    0.06
    ]]=
    0.06
    =='
    0.06
    want
    0.06
    Act Density 0.012%

    No Known Activations