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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of powers of two or exponent notation involving 2.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Hide
    -0.07
     montage
    -0.07
    пер
    -0.07
    brities
    -0.07
    _parse
    -0.07
    -girl
    -0.07
    YRO
    -0.06
    _preds
    -0.06
    fluid
    -0.06
     incorrectly
    -0.06
    POSITIVE LOGITS
    BeforeEach
    0.06
    lected
    0.06
    .l
    0.06
    олет
    0.06
     memorable
    0.06
    ��
    0.06
     Cascade
    0.06
    equalTo
    0.06
     direct
    0.06
    内の
    0.06
    Act Density 0.010%

    No Known Activations