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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gin
    -0.07
     overarching
    -0.07
     uni
    -0.06
     tedy
    -0.06
     изображ
    -0.06
    )은
    -0.06
    student
    -0.06
    ACY
    -0.06
    =?",
    -0.06
    astr
    -0.06
    POSITIVE LOGITS
    �
    0.10
     ke
    0.07
     bisa
    0.06
    票
    0.06
     Boutique
    0.06
     WS
    0.06
     Problem
    0.06
     outcomes
    0.06
    PRETTY
    0.06
    (reordered
    0.06
    Act Density 0.004%

    No Known Activations