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

    Neuronpedia

    INDEX
    Explanations

    graph adjacency

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the token “successors” (and related forms of “successor”) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ワ
    -0.06
     submar
    -0.06
    applications
    -0.06
    .Stdout
    -0.06
    ってきた
    -0.06
    International
    -0.06
    tems
    -0.06
     ApplicationException
    -0.06
    usalem
    -0.06
    /issues
    -0.06
    POSITIVE LOGITS
    าก
    0.07
     promoters
    0.07
     cong
    0.06
    _Att
    0.06
     erot
    0.06
     moments
    0.06
     flourish
    0.06
                       ↵
    0.06
     لع
    0.06
    (cos
    0.06
    Act Density 0.006%

    No Known Activations