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

    Neuronpedia

    INDEX
    Explanations

    variable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _intro
    -0.07
     wła
    -0.07
    uzu
    -0.07
    (QIcon
    -0.07
     Trucks
    -0.06
     일어
    -0.06
     ****
    -0.06
     Krishna
    -0.06
     Corruption
    -0.06
     Kits
    -0.06
    POSITIVE LOGITS
    monthly
    0.06
    urchase
    0.06
    (project
    0.06
     "".
    0.06
     documenting
    0.06
    代
    0.06
    ]):
↵
    0.06
     postpon
    0.06
    385
    0.06
    Prior
    0.06
    Act Density 0.008%

    No Known Activations