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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “through” (i.e. tokens containing the preposition “through”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.06
     mostr
    -0.06
     hiding
    -0.06
    更加
    -0.06
     mentioning
    -0.06
    _secs
    -0.06
    -auth
    -0.06
     creations
    -0.06
    ตรว
    -0.06
     предостав
    -0.06
    POSITIVE LOGITS
    입
    0.08
    	BYTE
    0.07
     (
↵
    0.07
    .idx
    0.06
    .value
    0.06
     sky
    0.06
     BOOL
    0.06
     )
    0.06
     elems
    0.06
    iPhone
    0.06
    Act Density 0.009%

    No Known Activations