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

    Neuronpedia

    INDEX
    Explanations

    Causes and effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     employed
    -0.07
     र
    -0.06
    annels
    -0.06
    ('../
    -0.06
     +=
    -0.06
    ("\\
    -0.06
    oute
    -0.06
    Toronto
    -0.06
     geh
    -0.05
     antivirus
    -0.05
    POSITIVE LOGITS
     الأمر
    0.08
    τός
    0.07
     temperatura
    0.06
    辛
    0.06
    SerializeField
    0.06
    ада
    0.06
     آیا
    0.06
     LT
    0.06
    ология
    0.06
     swingers
    0.06
    Act Density 0.438%

    No Known Activations