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

    Neuronpedia

    INDEX
    Explanations

    Forms of "to be"

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of first‐person self‐identification, i.e. tokens forming “I am” (including the contracted “‘m”) when the user states their role or identity.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sci
    -0.07
     runaway
    -0.06
    slug
    -0.06
     müc
    -0.06
    -pre
    -0.06
     hashtable
    -0.06
    xima
    -0.06
    욱
    -0.06
     Joy
    -0.06
     trials
    -0.06
    POSITIVE LOGITS
     stands
    0.07
    _Table
    0.07
    Parm
    0.06
    $form
    0.06
    (return
    0.06
     BEGIN
    0.06
    .Color
    0.06
     general
    0.06
     Desk
    0.06
     bot
    0.06
    Act Density 0.018%

    No Known Activations