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

    Neuronpedia

    INDEX
    Explanations

    harm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ==========
    -0.06
    quet
    -0.06
     раз
    -0.06
     fishes
    -0.06
    anean
    -0.06
     뒤
    -0.06
     JSONObject
    -0.06
    ساب
    -0.06
     mention
    -0.06
    ÄŸ
    -0.06
    POSITIVE LOGITS
    >↵↵↵
    0.08
    ！！
    0.07
     çiz
    0.07
    .Exit
    0.07
     Servers
    0.06
    iz
    0.06
     "↵
    0.06
     allergies
    0.06
    .union
    0.06
    VR
    0.06
    Act Density 0.000%

    No Known Activations