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

    Neuronpedia

    INDEX
    Explanations

    greetings, salutations

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the end‐of‐text (or end‐of‐turn) token (“<|eot_id|>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     summon
    -0.07
     suff
    -0.07
    725
    -0.07
    ogens
    -0.07
    Received
    -0.07
    451
    -0.07
     advent
    -0.07
    sort
    -0.06
    481
    -0.06
     trustworthy
    -0.06
    POSITIVE LOGITS
     modific
    0.07
    Bindable
    0.06
    ॉम
    0.06
     FormControl
    0.06
    (Level
    0.06
     poru
    0.06
     hugs
    0.06
    virtual
    0.06
    ?><
    0.06
    мерик
    0.06
    Act Density 0.016%

    No Known Activations