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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ox
    -0.07
    |^
    -0.07
    leşik
    -0.06
     Disease
    -0.06
     trx
    -0.06
     β
    -0.06
    -solving
    -0.06
     Book
    -0.06
     PET
    -0.06
     mitigate
    -0.06
    POSITIVE LOGITS
    قيق
    0.07
     globe
    0.06
    _general
    0.06
    ABEL
    0.06
    .camel
    0.06
     UIGraphics
    0.06
    уют
    0.06
    える
    0.06
    Рё
    0.06
    lobe
    0.06
    Act Density 0.006%

    No Known Activations