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

    Neuronpedia

    INDEX
    Explanations

    alt

    np_max-act · gemini-2.0-flash

    calculations related to inventory requirements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on decimal‐formatted numeric tokens (floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     responses
    -0.07
    ��
    -0.06
     Govern
    -0.06
     deletes
    -0.06
    cac
    -0.06
     CHK
    -0.06
     buses
    -0.06
    (xy
    -0.06
    660
    -0.06
    perf
    -0.06
    POSITIVE LOGITS
    像
    0.07
    ))){↵
    0.06
    ])))↵
    0.06
     Tôi
    0.06
    аліст
    0.06
    ресс
    0.06
    ')))↵
    0.06
     نیز
    0.06
    .MaximizeBox
    0.06
    '][$
    0.06
    Act Density 0.334%

    No Known Activations