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

    Neuronpedia

    INDEX
    Explanations

    carcinogen

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive—it does not respond to any tokens and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ailing
    -0.07
    .Options
    -0.06
    _Framework
    -0.06
    .CopyTo
    -0.06
    ESİ
    -0.06
     Liebe
    -0.06
     palabras
    -0.06
    persistent
    -0.06
    ajs
    -0.06
    ContentSize
    -0.06
    POSITIVE LOGITS
     данны
    0.06
    Cipher
    0.06
     debuted
    0.06
     Blick
    0.06
     Hoàng
    0.06
     fringe
    0.06
     inaugural
    0.06
     Ap
    0.06
    =length
    0.06
    (tcp
    0.06
    Act Density 0.009%

    No Known Activations