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

    Neuronpedia

    INDEX
    Explanations

    small amounts accumulating

    np_max-act · gemini-2.0-flash

    This neuron responds to instances of additive accumulation phrasing—especially the idiomatic “add up” (and its immediate context).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -html
    -0.06
    лід
    -0.06
    xies
    -0.06
    हर
    -0.06
    สมเด
    -0.06
    focused
    -0.06
    냥
    -0.06
    .@
    -0.06
    Дж
    -0.06
    vfs
    -0.06
    POSITIVE LOGITS
     ripped
    0.07
     worthy
    0.06
    _almost
    0.06
    \"><
    0.06
     @"\
    0.06
     chtě
    0.06
    ').'</
    0.06
    /tr
    0.06
     yelling
    0.06
    visibility
    0.06
    Act Density 0.019%

    No Known Activations