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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чает
    -0.07
    _THRESH
    -0.06
    online
    -0.06
    FontOfSize
    -0.06
    哈
    -0.06
    decoder
    -0.06
    BUTTON
    -0.06
    міну
    -0.06
    อค
    -0.06
     finer
    -0.06
    POSITIVE LOGITS
    systems
    0.07
     준비
    0.07
    orners
    0.07
     yönetim
    0.06
     yarış
    0.06
     необходимости
    0.06
    ●●●●●●●●●●●●●●●●
    0.06
     жін
    0.06
     Swimming
    0.06
     ')'
    0.06
    Act Density 0.002%

    No Known Activations