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

    Neuronpedia

    INDEX
    Explanations

    black

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Woody
    -0.07
    ��
    -0.07
    UpdateTime
    -0.07
     CommandLine
    -0.07
    909
    -0.07
     dny
    -0.07
     api
    -0.06
    970
    -0.06
     доч
    -0.06
    orque
    -0.06
    POSITIVE LOGITS
     Black
    0.17
    Black
    0.15
     black
    0.13
     BLACK
    0.12
    black
    0.10
    BLACK
    0.10
    /black
    0.08
    -black
    0.08
     blacks
    0.07
    :black
    0.07
    Act Density 0.021%

    No Known Activations