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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exposition
    -0.07
     терап
    -0.07
     amsterdam
    -0.06
    496
    -0.06
    arently
    -0.06
     reproductive
    -0.06
    429
    -0.06
    eyen
    -0.06
     refuses
    -0.06
     필요한
    -0.06
    POSITIVE LOGITS
    .hover
    0.06
     closet
    0.06
    _used
    0.06
    .rdf
    0.06
    ":""
    0.06
     сир
    0.06
     示例
    0.06
    	desc
    0.06
    pure
    0.06
    emon
    0.06
    Act Density 0.000%

    No Known Activations