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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash

    The neuron is essentially inactive—it never fires on any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Aluminum
    -0.06
     babes
    -0.06
    child
    -0.06
    _macro
    -0.06
     Glacier
    -0.06
     satire
    -0.06
    Acceleration
    -0.06
    ccd
    -0.06
    EUR
    -0.06
     inspection
    -0.06
    POSITIVE LOGITS
     Desired
    0.07
    ваются
    0.07
    .setTo
    0.06
     století
    0.06
    _ROT
    0.06
     různé
    0.06
    normally
    0.06
    :.:
    0.06
    _OPEN
    0.06
    DOCTYPE
    0.06
    Act Density 0.124%

    No Known Activations