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

    Neuronpedia

    INDEX
    Explanations

    'm

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the contraction “I’m,” i.e. the self-referential “I am” used in introductions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    =label
    -0.07
     facilit
    -0.06
    _wrap
    -0.06
    _MEMBER
    -0.06
     Found
    -0.06
     budget
    -0.06
    푸
    -0.06
    bi
    -0.06
    .fit
    -0.06
    -house
    -0.06
    POSITIVE LOGITS
     appId
    0.08
     ASTM
    0.07
    xmlns
    0.06
     výkon
    0.06
     Internacional
    0.06
    	BOOL
    0.06
    asctime
    0.06
     magically
    0.06
     ClassName
    0.06
     smaller
    0.06
    Act Density 0.027%

    No Known Activations