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

    Neuronpedia

    INDEX
    Explanations

    charge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (route
    -0.08
    Ň
    -0.07
    숀
    -0.07
     Harbour
    -0.07
    ome
    -0.07
     למצוא
    -0.07
    rzą
    -0.07
    уй
    -0.06
     souvenir
    -0.06
    osome
    -0.06
    POSITIVE LOGITS
    기술
    0.07
    cg
    0.07
    .mapping
    0.07
     theft
    0.06
     Kir
    0.06
    Clr
    0.06
     ..↵
    0.06
    Limits
    0.06
     AG
    0.06
     painfully
    0.06
    Act Density 0.013%

    No Known Activations