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

    Neuronpedia

    INDEX
    Explanations

    almost surely

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that mark types of stochastic convergence—especially the “a.s.”/“a.e.” abbreviations and words like “almost,” “surely,” and “probability.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     barrel
    -0.07
    세대
    -0.07
     guided
    -0.07
     preserves
    -0.07
    hev
    -0.07
     Tobias
    -0.06
     Jeh
    -0.06
     Hillary
    -0.06
     �
    -0.06
    David
    -0.06
    POSITIVE LOGITS
    thickness
    0.07
    dust
    0.07
    xba
    0.07
     administrators
    0.06
     ศร
    0.06
     enforcing
    0.06
     diploma
    0.06
    }%
    0.06
     traceback
    0.06
    groupBox
    0.06
    Act Density 0.003%

    No Known Activations