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

    Neuronpedia

    INDEX
    Explanations

    code, math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buds
    -0.07
    жень
    -0.06
     견
    -0.06
     ado
    -0.06
     apt
    -0.06
     CircularProgress
    -0.05
     whopping
    -0.05
    ul
    -0.05
     ní
    -0.05
     intense
    -0.05
    POSITIVE LOGITS
     radios
    0.07
    覚
    0.07
    Tick
    0.07
     Won
    0.07
     english
    0.07
    รถ
    0.06
     Sof
    0.06
    (sheet
    0.06
     aquel
    0.06
     تلاش
    0.06
    Act Density 0.000%

    No Known Activations