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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on the gerund “wanting” (as in “wanting to”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ergency
    -0.07
     ion
    -0.07
    _Play
    -0.06
     ******************************************************************************/↵↵
    -0.06
    습니다
    -0.06
    (coll
    -0.06
    uye
    -0.06
    ीए
    -0.06
     divergence
    -0.06
    .LA
    -0.06
    POSITIVE LOGITS
    からの
    0.06
    ]string
    0.06
    .repository
    0.06
    раниц
    0.06
    ilia
    0.06
     pokus
    0.06
     documenting
    0.06
    survey
    0.06
     Allen
    0.06
     Vaults
    0.06
    Act Density 0.005%

    No Known Activations