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

    Neuronpedia

    INDEX
    Explanations

    capacity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ack
    -0.06
    dst
    -0.06
    大學
    -0.06
    其实
    -0.06
    Qi
    -0.06
     issu
    -0.06
     ayar
    -0.06
    ucer
    -0.06
    ैं,
    -0.06
    -carousel
    -0.06
    POSITIVE LOGITS
     unread
    0.07
    ]){↵
    0.07
     apologize
    0.07
    ITA
    0.06
    ури
    0.06
    :*
    0.06
    _ABORT
    0.06
     Horse
    0.06
    禮
    0.06
    Grad
    0.06
    Act Density 0.256%

    No Known Activations