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

    Neuronpedia

    INDEX
    Explanations

    oil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pública
    -0.08
     arrange
    -0.07
    一句
    -0.07
     equivalents
    -0.07
    ℃
    -0.07
     classifications
    -0.07
    自学
    -0.07
     suit
    -0.06
     Wildlife
    -0.06
     Sheet
    -0.06
    POSITIVE LOGITS
    _RANDOM
    0.08
    蕞
    0.07
     relationship
    0.07
     delegation
    0.07
     redirection
    0.07
    𝙿
    0.07
    特斯拉
    0.06
    (one
    0.06
    غل
    0.06
    מקד
    0.06
    Act Density 0.066%

    No Known Activations