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

    Neuronpedia

    INDEX
    Explanations

    recognizable features or elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.51
     Rafael
    0.45
    itories
    0.44
     Maximum
    0.44
    ทาง
    0.43
     servo
    0.43
    爱好者
    0.43
    ك
    0.42
     Track
    0.42
     Samuel
    0.41
    POSITIVE LOGITS
    funciones
    0.45
    buildings
    0.44
    changed
    0.43
    newName
    0.43
     restructuring
    0.42
     изменить
    0.42
     кофе
    0.42
    refreshToken
    0.42
     demais
    0.41
    transform
    0.41
    Act Density 0.004%

    No Known Activations