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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fully
    -0.07
    _YELLOW
    -0.06
     هفت
    -0.06
     батьків
    -0.06
    -CN
    -0.06
    acades
    -0.06
     Songs
    -0.06
    /css
    -0.06
     Seventh
    -0.06
     Trees
    -0.06
    POSITIVE LOGITS
    data
    0.07
     aim
    0.07
     이번
    0.07
    İ
    0.06
    heap
    0.06
     tapi
    0.06
    -data
    0.06
    !='
    0.06
     anlat
    0.06
     چیست
    0.06
    Act Density 0.003%

    No Known Activations