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

    Neuronpedia

    INDEX
    Explanations

    culture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <W
    -0.07
     offers
    -0.07
    _enabled
    -0.07
    itution
    -0.06
    &w
    -0.06
    framework
    -0.06
    Il
    -0.06
    telegram
    -0.06
    $c
    -0.06
    (k
    -0.06
    POSITIVE LOGITS
    摒
    0.07
     сраз
    0.07
    风尚
    0.07
    心目
    0.07
     üst
    0.07
     daytime
    0.06
    会同
    0.06
     cannabinoids
    0.06
    �
    0.06
     맞
    0.06
    Act Density 0.035%

    No Known Activations