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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects the word “by” when it appears in passive causal constructions (as in “caused by”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    езульт
    -0.07
     ";
↵
    -0.07
    Markers
    -0.07
    Mutation
    -0.07
     самым
    -0.06
    osphate
    -0.06
    (menu
    -0.06
     rubber
    -0.06
    _module
    -0.06
    än
    -0.06
    POSITIVE LOGITS
     그리
    0.07
     söy
    0.07
     parfait
    0.06
     :+:
    0.06
     информ
    0.06
    年に
    0.06
     LP
    0.06
     ah
    0.06
     الى
    0.06
     Mayıs
    0.06
    Act Density 0.001%

    No Known Activations