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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مد
    -0.07
    ("{
    -0.07
    ्यव
    -0.06
     peri
    -0.06
    ured
    -0.06
    ="_
    -0.06
    jest
    -0.06
    enary
    -0.06
    vj
    -0.06
    ce
    -0.06
    POSITIVE LOGITS
    LastError
    0.07
    (app
    0.07
     clearTimeout
    0.07
     سابق
    0.06
     *.
    0.06
     tucked
    0.06
     مركز
    0.06
     خص
    0.06
     StringSplitOptions
    0.06
     disagreed
    0.06
    Act Density 0.046%

    No Known Activations