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

    Neuronpedia

    INDEX
    Explanations

    code/configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contraceptive
    -0.07
     Layers
    -0.06
    .Duration
    -0.06
     Freem
    -0.06
    	st
    -0.06
    _IO
    -0.06
    .Upload
    -0.06
     Cecil
    -0.06
    _Delay
    -0.06
    _blocking
    -0.06
    POSITIVE LOGITS
     kleinen
    0.06
    롱
    0.06
     failing
    0.06
     documented
    0.06
     завжди
    0.06
     είναι
    0.06
    (nd
    0.06
     frying
    0.06
    пат
    0.06
    тен
    0.06
    Act Density 0.078%

    No Known Activations