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

    Neuronpedia

    INDEX
    Explanations

    academic/technical writing

    np_max-act · gemini-2.0-flash

    The neuron fires on words expressing possibility or uncertainty—modal and hedging terms such as “can,” “may,” “help,” and “potentially.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     может
    -0.07
     facilit
    -0.06
     Dedicated
    -0.06
     explo
    -0.06
    	cc
    -0.06
    ASF
    -0.06
    aines
    -0.06
     Aside
    -0.06
     دادن
    -0.06
    Instantiate
    -0.06
    POSITIVE LOGITS
    .mongo
    0.07
     truck
    0.06
    (opt
    0.06
     Ли
    0.06
     Sexe
    0.06
    :"",↵
    0.06
    .VisualStudio
    0.06
     موج
    0.06
    *R
    0.06
    ؤول
    0.06
    Act Density 0.085%

    No Known Activations