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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash

    The neuron fires on the special control/header markers (e.g. “<|start_header_id|>”) used to delineate message metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    еп
    -0.07
     autoComplete
    -0.06
    ceiver
    -0.06
    aturity
    -0.06
     Supervisor
    -0.06
    .getOrElse
    -0.06
     Fly
    -0.06
    ****************************************************************
    -0.06
    ScrollView
    -0.06
    osomes
    -0.06
    POSITIVE LOGITS
     depend
    0.07
     Runs
    0.07
    に向
    0.07
     fotograf
    0.06
     putchar
    0.06
     vysvět
    0.06
     offense
    0.06
    Pic
    0.06
     resilient
    0.06
    rita
    0.06
    Act Density 0.048%

    No Known Activations