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

    Neuronpedia

    INDEX
    Explanations

    behave

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Big
    -0.06
    _artist
    -0.06
    	win
    -0.06
    _re
    -0.06
    ┴
    -0.06
    ITICAL
    -0.06
     título
    -0.06
     EXT
    -0.06
     варт
    -0.06
    telefono
    -0.06
    POSITIVE LOGITS
    eria
    0.06
     retali
    0.06
    wat
    0.06
     blockDim
    0.06
    vida
    0.06
     kendisine
    0.06
    tul
    0.06
     amidst
    0.06
    blas
    0.06
     Praze
    0.06
    Act Density 0.007%

    No Known Activations