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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act · gemini-2.0-flash

    The neuron fires on YAML‐style metadata markers—specifically the “!” tag prefix and “&” anchor symbol.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Dic
    -0.07
     vieux
    -0.07
     unos
    -0.07
     рек
    -0.07
    REQ
    -0.07
     Crow
    -0.06
     tasked
    -0.06
     weakened
    -0.06
    。↵↵↵↵↵↵
    -0.06
    Dur
    -0.06
    POSITIVE LOGITS
     fontFamily
    0.07
    -your
    0.06
    -With
    0.06
    NodeId
    0.06
    Know
    0.06
    τητα
    0.06
     illustration
    0.06
    .createElement
    0.06
     acquired
    0.06
    atively
    0.06
    Act Density 0.000%

    No Known Activations