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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the “FTP” protocol (e.g. “FTP” in connector names and polling contexts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ар
    -0.06
     darling
    -0.06
     foam
    -0.06
     Succ
    -0.06
     Giang
    -0.06
    att
    -0.06
    Reserved
    -0.06
     služ
    -0.06
    .palette
    -0.06
    _ATTACH
    -0.06
    POSITIVE LOGITS
     appName
    0.06
     verschiedene
    0.06
    .Popen
    0.06
     opi
    0.06
     horns
    0.06
     cé
    0.06
     몽
    0.06
     dys
    0.06
    essaging
    0.06
    uebas
    0.06
    Act Density 0.400%

    No Known Activations