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

    Neuronpedia

    INDEX
    Explanations

    European resort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     technique
    0.44
     method
    0.42
     Method
    0.41
     विधे
    0.41
    ission
    0.40
    听说
    0.40
    },$
    0.40
    peas
    0.39
    Method
    0.38
    method
    0.38
    POSITIVE LOGITS
     nhóm
    0.59
     الشباب
    0.47
    ầu
    0.47
    กลุ่ม
    0.47
     각각
    0.46
     rõ
    0.45
     સંપ
    0.45
     تھے۔
    0.44
    โดย
    0.44
     eslint
    0.44
    Act Density 0.005%

    No Known Activations