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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron flags exhortative or appeal phrases where someone “calls on” or “urges” a group “to” do something.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     webs
    -0.06
    анта
    -0.06
    quelle
    -0.06
     Citizen
    -0.06
    Crime
    -0.06
    RecyclerView
    -0.06
     Carroll
    -0.06
     EDM
    -0.06
     Deleted
    -0.06
     loose
    -0.06
    POSITIVE LOGITS
    .MOUSE
    0.07
    ↵↵↵↵↵↵↵↵↵↵
    0.07
    toEqual
    0.07
     orderly
    0.07
    .className
    0.06
     fread
    0.06
    trad
    0.06
    .poly
    0.06
    -->
↵
    0.06
     xmax
    0.06
    Act Density 0.027%

    No Known Activations