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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    馃
    -0.07
    又能
    -0.06
    "io
    -0.06
     ملف
    -0.06
     cú
    -0.06
    すぐ
    -0.06
    💒
    -0.06
    哢
    -0.06
     interfere
    -0.06
    ހ
    -0.06
    POSITIVE LOGITS
     BMI
    0.08
     System
    0.08
    	System
    0.07
     Currently
    0.07
     Sheldon
    0.07
    rid
    0.07
    大熊猫
    0.07
     Hispanic
    0.07
    .communic
    0.07
    emale
    0.06
    Act Density 0.000%

    No Known Activations