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

    Neuronpedia

    INDEX
    Explanations

    JSON schema

    np_max-act · gemini-2.0-flash

    The neuron is essentially dead—it never activates on any input and thus isn’t detecting any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .PO
    -0.07
     sea
    -0.06
     Cafe
    -0.06
    NGC
    -0.06
     returnType
    -0.06
    ｱ
    -0.06
    .depend
    -0.06
     Sum
    -0.06
    .Ge
    -0.06
    :$
    -0.06
    POSITIVE LOGITS
     masculinity
    0.07
    ليات
    0.06
     Đảng
    0.06
    desktop
    0.06
    thritis
    0.06
     Russell
    0.06
     draft
    0.06
    communications
    0.06
    ざ
    0.06
     visibility
    0.06
    Act Density 0.001%

    No Known Activations