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

    Neuronpedia

    INDEX
    Explanations

    pr

    np_max-act · gemini-2.0-flash

    This neuron activates on phonetic‐pronunciation segments (IPA or respelling bits) in dictionary‐style entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lantern
    -0.07
    	Camera
    -0.06
    Intl
    -0.06
     Karn
    -0.06
    殊
    -0.06
     cares
    -0.06
    けない
    -0.06
     carrying
    -0.06
     Comparative
    -0.06
     svém
    -0.06
    POSITIVE LOGITS
    _pas
    0.07
     kalp
    0.07
    _normalize
    0.07
     jeg
    0.07
    dst
    0.07
    liches
    0.07
    _]
    0.07
    �
    0.06
     và
    0.06
    ListGroup
    0.06
    Act Density 0.102%

    No Known Activations