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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron predominantly fires on verbs that describe characters’ movements or changes in physical location.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    erable
    -0.07
     Méd
    -0.06
    पर
    -0.06
    .*
    -0.06
     Lit
    -0.06
    /site
    -0.06
    =b
    -0.06
     Flour
    -0.06
     Bir
    -0.06
    بر
    -0.06
    POSITIVE LOGITS
    本当に
    0.06
    	open
    0.06
    ottie
    0.06
     "('
    0.06
    different
    0.06
    .usermodel
    0.06
    -related
    0.06
     Ivanka
    0.06
    อกจาก
    0.06
     ⓘ
    0.06
    Act Density 0.051%

    No Known Activations