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

    Neuronpedia

    INDEX
    Explanations

    Excerpts from longer texts

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the assistant’s “answers,” i.e. references to its own responses in the instruction text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (style
    -0.07
    hide
    -0.07
     FileMode
    -0.06
    StatusCode
    -0.06
     mü
    -0.06
    However
    -0.06
    ерами
    -0.06
    드
    -0.06
    /action
    -0.06
    _legend
    -0.06
    POSITIVE LOGITS
    [ii
    0.07
    eným
    0.06
    Empleado
    0.06
     medida
    0.06
     برابر
    0.06
    Front
    0.06
    нулась
    0.06
    prehensive
    0.06
     obec
    0.06
     cov
    0.06
    Act Density 0.010%

    No Known Activations