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

    Neuronpedia

    INDEX
    Explanations

    commute

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    كري
    -0.07
    诗
    -0.07
     expressly
    -0.07
    cliente
    -0.07
    �
    -0.07
     so
    -0.07
    李
    -0.07
    整整
    -0.07
    砰
    -0.07
     così
    -0.07
    POSITIVE LOGITS
    (Web
    0.07
    Css
    0.07
    _reduction
    0.07
    ]("
    0.07
     кат
    0.07
     Guards
    0.06
     neighbourhood
    0.06
    (Result
    0.06
    Adventure
    0.06
     konuşma
    0.06
    Act Density 0.003%

    No Known Activations