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

    Neuronpedia

    INDEX
    Explanations

    arithmetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inal
    -0.07
     Goddess
    -0.07
    ungal
    -0.07
    ungalow
    -0.06
     Templ
    -0.06
    _el
    -0.06
    ylon
    -0.06
    league
    -0.06
     Микола
    -0.06
    ADIO
    -0.06
    POSITIVE LOGITS
     Arithmetic
    0.09
     arithmetic
    0.08
    0.07
    (Math
    0.07
     Comp
    0.07
    ---@
    0.06
    режд
    0.06
    feas
    0.06
     mainAxisAlignment
    0.06
     Garrett
    0.06
    Act Density 0.002%

    No Known Activations