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

    Neuronpedia

    INDEX
    Explanations

    Making things better

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of improvements or the need/room for improvement in a discussion.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Photos
    -0.06
     dummy
    -0.06
     synonym
    -0.06
    Arduino
    -0.06
     Executors
    -0.06
    (ierr
    -0.06
    _ORIENTATION
    -0.06
    ObjectName
    -0.06
     различ
    -0.06
     آل
    -0.06
    POSITIVE LOGITS
    shall
    0.07
     Morton
    0.06
    ells
    0.06
    _roles
    0.06
    шов
    0.06
     bere
    0.06
    ленный
    0.06
    akin
    0.06
     тоб
    0.06
    ，将
    0.06
    Act Density 0.021%

    No Known Activations