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

    Neuronpedia

    INDEX
    Explanations

    Register

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the term “register,” flagging registration‐related instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _softmax
    -0.07
     действия
    -0.06
     дод
    -0.06
    Some
    -0.06
    apture
    -0.06
    乎
    -0.06
    ادث
    -0.06
     showcases
    -0.06
    code
    -0.06
    .writeObject
    -0.06
    POSITIVE LOGITS
    NL
    0.06
    CRY
    0.06
     longtime
    0.06
     firm
    0.06
    .ndarray
    0.06
     RF
    0.06
    обра�
    0.06
     піш
    0.06
     SCHOOL
    0.06
     declaration
    0.06
    Act Density 0.000%

    No Known Activations