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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act · gemini-2.0-flash

    The neuron doesn’t respond to any tokens—it remains inactive and thus doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    irical
    -0.07
    .wrap
    -0.06
     Lic
    -0.06
    系統
    -0.06
    宇
    -0.06
     yayım
    -0.06
     grassroots
    -0.06
     ам
    -0.06
     estruct
    -0.06
     heuristic
    -0.06
    POSITIVE LOGITS
     захворю
    0.07
    -",
    0.07
    AREA
    0.07
     второй
    0.07
     porno
    0.07
    hw
    0.06
    ＠
    0.06
     Patterson
    0.06
     دیگری
    0.06
    ={(
    0.06
    Act Density 0.016%

    No Known Activations