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 fires on occurrences of the auxiliary “be” (and similar forms) when it’s used to form a passive construction (i.e. “be” + past participle).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .dll
    -0.07
    Font
    -0.07
     Dünya
    -0.07
     ceremon
    -0.07
     �
    -0.06
     Listening
    -0.06
    offee
    -0.06
     Today
    -0.06
    ytut
    -0.06
     så
    -0.06
    POSITIVE LOGITS
     be
    0.08
    َ
    0.07
     indefinite
    0.07
    ine
    0.07
    se
    0.07
    be
    0.07
    able
    0.07
    ��
    0.06
    (be
    0.06
    َّ
    0.06
    Act Density 0.014%

    No Known Activations