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

    Neuronpedia

    INDEX
    Explanations

    Omission

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens indicating omitted or continued content—particularly ellipsis (“...”) or words like “more” that signal truncation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     distinctive
    -0.07
     similarity
    -0.06
     apparel
    -0.06
    (Uri
    -0.06
    etto
    -0.06
    	score
    -0.06
    (init
    -0.06
     opcode
    -0.06
     attributable
    -0.06
     matched
    -0.06
    POSITIVE LOGITS
    .foo
    0.07
     NPC
    0.07
    idak
    0.07
    Česk
    0.06
    /Public
    0.06
     Genetic
    0.06
     Sb
    0.06
    Added
    0.06
     dernière
    0.06
    168
    0.06
    Act Density 0.027%

    No Known Activations