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

    Neuronpedia

    INDEX
    Explanations

    different writing styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nanoc
    0.41
    ཝ
    0.40
    耆
    0.39
    檜
    0.39
     kuv
    0.37
     snee
    0.37
    AddModelError
    0.37
     denoting
    0.37
    ็ม
    0.36
    னியா
    0.36
    POSITIVE LOGITS
    Australia
    0.72
     Australia
    0.71
     Австра
    0.68
    Melbourne
    0.67
     Melbourne
    0.66
     Australian
    0.64
    Austral
    0.64
    Australian
    0.64
     ऑस्ट्रेलिया
    0.64
    澳洲
    0.64
    Act Density 0.001%

    No Known Activations