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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on mentions of dice and dice‐rolling (e.g. “roll,” “the,” “dice”), effectively detecting references to rolling a die.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    _pulse
    -0.07
    .Highlight
    -0.06
     जर
    -0.06
    ولد
    -0.06
     Masters
    -0.06
     �
    -0.06
     ts
    -0.06
    dbe
    -0.06
     jí
    -0.06
    POSITIVE LOGITS
    /small
    0.07
    upert
    0.07
    Sdk
    0.06
    FormsModule
    0.06
     Novel
    0.06
    anean
    0.06
     Timothy
    0.06
     barrels
    0.06
     anne
    0.06
    Submit
    0.06
    Act Density 0.003%

    No Known Activations