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

    Neuronpedia

    INDEX
    Explanations

    digits, defying, someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fins
    0.49
     اح
    0.49
    it
    0.47
     tank
    0.47
     r
    0.46
     watch
    0.46
     carburetor
    0.46
     sump
    0.46
     intention
    0.45
    ...(
    0.44
    POSITIVE LOGITS
    鶘
    0.60
     ተጨማሪ
    0.56
    儩
    0.54
    ovaných
    0.53
    είο
    0.52
     ምክንያት
    0.51
    า
    0.51
    ITIONAL
    0.50
     जिल्हा
    0.50
     Polícia
    0.50
    Act Density 0.000%

    No Known Activations