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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on numeric tokens representing decimal or fractional values (e.g. “0.40478515625,” “2.529296875,” “–0.367919921875,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    lediği
    -0.07
    .HttpContext
    -0.07
     crem
    -0.06
     lors
    -0.06
     поли
    -0.06
    ubbo
    -0.06
    SSFWorkbook
    -0.06
    '][]
    -0.06
     uploaded
    -0.06
    .Trans
    -0.06
    POSITIVE LOGITS
    sg
    0.08
     Conn
    0.07
    ประกอบ
    0.06
    \n
    0.06
     другие
    0.06
    addAction
    0.06
     provid
    0.06
     Cooperation
    0.06
    Pet
    0.06
     všechny
    0.06
    Act Density 0.019%

    No Known Activations