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

    Neuronpedia

    INDEX
    Explanations

    fresh

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, especially floating‐point numbers and decimal measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     حو
    -0.06
    _feat
    -0.06
    hatt
    -0.06
     workshops
    -0.06
    */}↵
    -0.06
    HasForeignKey
    -0.06
     κρα
    -0.06
     카지노
    -0.06
     detecting
    -0.06
     Died
    -0.06
    POSITIVE LOGITS
    侵
    0.07
     gore
    0.07
    ahren
    0.06
     taj
    0.06
     ripped
    0.06
     Bust
    0.06
    근
    0.06
    __(*
    0.06
     contentType
    0.06
     batting
    0.06
    Act Density 0.290%

    No Known Activations