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

    Neuronpedia

    INDEX
    Explanations

    nov

    np_max-act · gemini-2.0-flash

    This neuron detects the formal taxonomic “sp. nov.” pattern used to name a newly proposed species.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -ag
    -0.06
     sollen
    -0.06
    -seat
    -0.06
    .safe
    -0.06
     concede
    -0.06
    ند
    -0.06
    +a
    -0.06
    -running
    -0.06
    Met
    -0.06
    凡
    -0.06
    POSITIVE LOGITS
     incentives
    0.06
     рекоменда
    0.06
    OptionsMenu
    0.06
     tarihi
    0.06
    "os
    0.06
     ülke
    0.06
    (tk
    0.06
    Ctrl
    0.06
    διο
    0.06
    ."]↵
    0.06
    Act Density 0.008%

    No Known Activations