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

    Neuronpedia

    INDEX
    Explanations

    items left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spacing
    -0.08
     casting
    -0.08
    urie
    -0.08
    Spacing
    -0.08
     mantra
    -0.08
     justify
    -0.07
    :UI
    -0.07
     toca
    -0.07
    Casting
    -0.07
    برى
    -0.07
    POSITIVE LOGITS
    剩
    0.14
    _remaining
    0.13
     surviving
    0.13
     após
    0.12
    Remaining
    0.12
     Remaining
    0.12
     leftover
    0.12
     survivors
    0.12
    .remaining
    0.12
     remaining
    0.11
    Act Density 0.053%

    No Known Activations