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

    Neuronpedia

    INDEX
    Explanations

    Code/Machine Learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ına
    -0.07
    Geo
    -0.07
     potentials
    -0.06
    ulton
    -0.06
    振り
    -0.06
    _cat
    -0.06
    ewis
    -0.06
    317
    -0.06
    kernel
    -0.06
     sung
    -0.06
    POSITIVE LOGITS
     φορ
    0.07
    Specific
    0.07
     Ú
    0.07
     Hort
    0.07
     prosper
    0.06
     jaký
    0.06
     ing
    0.06
     destruct
    0.06
    Bonjour
    0.06
     Original
    0.06
    Act Density 0.001%

    No Known Activations