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

    Neuronpedia

    INDEX
    Explanations

    superclass

    np_max-act · gemini-2.0-flash

    The neuron is looking for floating-point numeric literals (decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     underrated
    -0.08
     �
    -0.07
     cleric
    -0.07
    .pat
    -0.07
     loaf
    -0.06
     Sammy
    -0.06
     azi
    -0.06
    _PLATFORM
    -0.06
     interpreted
    -0.06
     bunların
    -0.06
    POSITIVE LOGITS
     endorsement
    0.07
    -date
    0.07
    meld
    0.06
    iquer
    0.06
    utes
    0.06
    692
    0.06
    сі
    0.06
     μόνο
    0.06
    /format
    0.06
     кв
    0.06
    Act Density 0.118%

    No Known Activations