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

    Neuronpedia

    INDEX
    Explanations

    finances

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric constants (especially floating‐point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Checkbox
    -0.06
     �
    -0.06
    Charge
    -0.06
    wel
    -0.06
    Animator
    -0.06
    有限
    -0.06
     Naruto
    -0.06
    kar
    -0.06
    _salary
    -0.06
     acad
    -0.06
    POSITIVE LOGITS
     nomin
    0.08
    weakSelf
    0.06
    за
    0.06
     χρησιμοποι
    0.06
    .ศ
    0.06
     Nombre
    0.06
    рек
    0.06
     possibility
    0.06
    가격
    0.06
    ，就
    0.06
    Act Density 0.025%

    No Known Activations