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

    Neuronpedia

    INDEX
    Explanations

    source code style conventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arsenal
    -0.09
    _wrapper
    -0.09
    flammatory
    -0.09
     ממנו
    -0.08
    (copy
    -0.08
     beil
    -0.08
    _copy
    -0.08
     בית
    -0.08
    disp
    -0.08
     abaf
    -0.08
    POSITIVE LOGITS
     geared
    0.09
     ตาม
    0.08
     spacecraft
    0.08
     cm
    0.07
    หน้
    0.07
     และ
    0.07
     practicing
    0.07
    0.07
     convention
    0.07
     tutta
    0.07
    Act Density 0.002%
    No Known Activations