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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron never fires on any of the example tokens—it appears to be effectively “dead” and does not detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    olu
    -0.08
     comprehension
    -0.07
    [
    -0.07
     originates
    -0.07
    ILINE
    -0.06
     Sodium
    -0.06
     evaluates
    -0.06
    Submitting
    -0.06
    preh
    -0.06
    revolution
    -0.06
    POSITIVE LOGITS
     ct
    0.07
    �
    0.06
    енням
    0.06
     fuer
    0.06
    assen
    0.06
     fs
    0.06
     région
    0.06
     Homer
    0.06
     Exist
    0.06
     atención
    0.06
    Act Density 0.090%

    No Known Activations