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

    Neuronpedia

    INDEX
    Explanations

    PL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     交
    -0.07
    ازم
    -0.06
    话
    -0.06
    .Max
    -0.06
     nech
    -0.06
     Bias
    -0.06
     ◆
    -0.06
     рассчит
    -0.06
    ButtonItem
    -0.06
    ADDE
    -0.06
    POSITIVE LOGITS
     pretending
    0.07
     unconventional
    0.07
    ’i
    0.06
    levard
    0.06
     upset
    0.06
    东西
    0.06
     universe
    0.06
    _gettime
    0.06
     Backpack
    0.06
    gres
    0.06
    Act Density 0.001%

    No Known Activations