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

    Neuronpedia

    INDEX
    Explanations

    apologies and technical issues

    np_max-act · gemini-2.0-flash

    The neuron fires on informal apologies or admissions of difficulty (e.g. “sorry for the bad angle,” “it’s hard holding it here while taking a shot”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bel
    -0.07
    type
    -0.07
     Selected
    -0.07
     CUSTOM
    -0.07
    集中
    -0.07
     attorney
    -0.07
     nebo
    -0.06
     nutné
    -0.06
     nn
    -0.06
     输入
    -0.06
    POSITIVE LOGITS
     forEach
    0.06
    CppGuid
    0.06
    andum
    0.06
     useMemo
    0.06
    	boolean
    0.06
    pga
    0.06
    	describe
    0.06
     pedigree
    0.05
    fps
    0.05
    feof
    0.05
    Act Density 0.036%

    No Known Activations