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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron is picking up on mentions of default settings and overriding or customizing those defaults (e.g. “default,” “override,” “selected,” “modifying”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _td
    -0.07
    ')]↵
    -0.07
     луч
    -0.07
     mejor
    -0.07
     empresas
    -0.06
    -t
    -0.06
    psi
    -0.06
    escription
    -0.06
     которое
    -0.06
    yl
    -0.06
    POSITIVE LOGITS
    Tôi
    0.07
     blockDim
    0.06
    rotate
    0.06
    йн
    0.06
     Mathematic
    0.06
    -con
    0.06
     nighttime
    0.06
    λία
    0.06
     viewBox
    0.06
     unmarried
    0.06
    Act Density 0.056%

    No Known Activations