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

    Neuronpedia

    INDEX
    Explanations

    lists and reports

    np_max-act · gemini-2.0-flash

    This neuron never activates on any tokens—it does not detect any consistent pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mons
    -0.07
     Buk
    -0.07
    ěti
    -0.07
    ěstí
    -0.06
    -Bar
    -0.06
     Apocalypse
    -0.06
    anca
    -0.06
    .sock
    -0.06
    ΙΟ
    -0.06
     Monaco
    -0.06
    POSITIVE LOGITS
     conexión
    0.06
    /;↵
    0.06
    促
    0.06
    ../
    0.06
    _TIMER
    0.06
    ordered
    0.06
    "],
    0.06
     */↵↵↵
    0.06
    Aside
    0.06
    Cook
    0.05
    Act Density 0.275%

    No Known Activations