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

    Neuronpedia

    INDEX
    Explanations

    erad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    washer
    -0.07
    ificador
    -0.07
     hiçbir
    -0.06
     budd
    -0.06
    Marker
    -0.06
     raspberry
    -0.06
     Both
    -0.06
    Both
    -0.06
    となり
    -0.06
     المح
    -0.06
    POSITIVE LOGITS
    \Config
    0.07
     outcomes
    0.07
    ord
    0.06
    .provider
    0.06
    (word
    0.06
     ngân
    0.06
    ternal
    0.06
    FONT
    0.06
    rotein
    0.06
     хви
    0.06
    Act Density 0.003%

    No Known Activations