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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    庭
    -0.07
    Á
    -0.07
    .training
    -0.07
    ADOS
    -0.07
    Player
    -0.06
     terrace
    -0.06
     thuốc
    -0.06
    Keys
    -0.06
    	while
    -0.06
    AIR
    -0.06
    POSITIVE LOGITS
     용
    0.07
    ooth
    0.07
    utilus
    0.06
    اة
    0.06
     Zucker
    0.06
     männ
    0.06
     trademark
    0.06
     Athens
    0.06
    orida
    0.06
    alizace
    0.06
    Act Density 0.069%

    No Known Activations