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

    Neuronpedia

    INDEX
    Explanations

    black

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by the word “black” (including compounds that start with “black”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fmt
    -0.08
    _trim
    -0.07
    fstream
    -0.07
     interpolate
    -0.07
     提
    -0.07
     WebDriverWait
    -0.07
     Trem
    -0.07
     namoro
    -0.07
     uyum
    -0.07
     Willow
    -0.07
    POSITIVE LOGITS
     Black
    0.17
    Black
    0.14
     black
    0.14
     BLACK
    0.13
    black
    0.13
     blacklist
    0.11
    BLACK
    0.10
     blackout
    0.09
     Blacks
    0.08
    /black
    0.08
    Act Density 0.020%

    No Known Activations