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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    The neuron is keyed to occurrences of the auxiliary “be” (and its closely related passive-voice or infinitive forms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tell
    -0.08
    arrass
    -0.07
     LANG
    -0.07
     video
    -0.07
     آذ
    -0.07
    wagon
    -0.06
    idders
    -0.06
     region
    -0.06
    road
    -0.06
    talk
    -0.06
    POSITIVE LOGITS
     adjustable
    0.07
     be
    0.07
     şeklinde
    0.07
     Be
    0.07
     사용
    0.07
    	be
    0.07
     seq
    0.06
    .Be
    0.06
     организации
    0.06
    (fileName
    0.06
    Act Density 0.025%

    No Known Activations