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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash

    The neuron is triggered by floating‐point number tokens (decimal numerals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    eworthy
    -0.07
    に関
    -0.06
     funct
    -0.06
    �
    -0.06
     suitable
    -0.06
    hsi
    -0.06
     advant
    -0.06
    weekday
    -0.06
    ronym
    -0.06
    Reduc
    -0.06
    POSITIVE LOGITS
     Around
    0.08
     over
    0.08
     tops
    0.08
     contour
    0.07
                               ↵
    0.07
     underwater
    0.07
     uit
    0.07
     everywhere
    0.07
     Down
    0.07
     contours
    0.07
    Act Density 0.007%

    No Known Activations