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

    Neuronpedia

    INDEX
    Explanations

    Thrusting

    np_max-act · gemini-2.0-flash

    The neuron never activates on any token—it appears to be essentially “dead” and finds nothing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .combine
    -0.07
    _bot
    -0.06
    291
    -0.06
    atır
    -0.06
    .threshold
    -0.06
     factions
    -0.06
    (seconds
    -0.06
     chubby
    -0.06
     Phantom
    -0.06
     Наз
    -0.06
    POSITIVE LOGITS
    .ordinal
    0.07
    력이
    0.07
    력
    0.07
    Ath
    0.07
    Rew
    0.06
    商
    0.06
     ldc
    0.06
    orus
    0.06
    并
    0.06
    .control
    0.06
    Act Density 0.012%

    No Known Activations