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

    Neuronpedia

    INDEX
    Explanations

    Mathematical expressions with exponents

    np_max-act · gemini-2.0-flash

    The neuron fires on the single‐letter variable names (like x, y, z, r, k, etc.) used in algebraic terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    PropertyValue
    -0.07
     Pett
    -0.06
    _fit
    -0.06
    _handler
    -0.06
    earer
    -0.06
    ařilo
    -0.06
    _iteration
    -0.06
    thren
    -0.06
    amide
    -0.06
    ęki
    -0.06
    POSITIVE LOGITS
    Education
    0.06
     uy
    0.06
    SPORT
    0.06
     SEN
    0.06
     nightlife
    0.06
     ук
    0.06
    Alice
    0.06
     ž
    0.06
     rehabilitation
    0.06
     imaging
    0.06
    Act Density 0.005%

    No Known Activations