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

    Neuronpedia

    INDEX
    Explanations

    unpublished

    np_max-act · gemini-2.0-flash

    This neuron detects citations or mentions of “unpublished” data or results in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Solver
    -0.07
    Fo
    -0.07
     Enough
    -0.07
     Decode
    -0.06
     Cool
    -0.06
    Translations
    -0.06
    (sol
    -0.06
    Icons
    -0.06
    ォ
    -0.06
     Weed
    -0.06
    POSITIVE LOGITS
    �
    0.07
     Crimson
    0.07
    .internal
    0.06
    ocyte
    0.06
    0.06
    0.06
     wardrobe
    0.06
     GOOGLE
    0.06
     Dun
    0.06
     ژان
    0.06
    Act Density 0.004%

    No Known Activations