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

    Neuronpedia

    INDEX
    Explanations

    hardware and drivers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zero
    -0.07
    hydr
    -0.07
    су
    -0.07
     sunscreen
    -0.06
     doktor
    -0.06
    VISIBLE
    -0.06
     sü
    -0.06
    /div
    -0.06
    _lines
    -0.06
    postal
    -0.06
    POSITIVE LOGITS
     alleges
    0.06
     IRQ
    0.06
    WindowTitle
    0.06
    _primitive
    0.05
     fray
    0.05
     haired
    0.05
     redefine
    0.05
    ___↵↵
    0.05
     descending
    0.05
    compileComponents
    0.05
    Act Density 0.011%

    No Known Activations