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

    Neuronpedia

    INDEX
    Explanations

    specific number or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leng
    0.47
    нача
    0.44
     lengths
    0.44
    Leng
    0.42
     lenght
    0.41
     Panjang
    0.40
     panjang
    0.39
     beve
    0.39
     länger
    0.37
     vän
    0.37
    POSITIVE LOGITS
    你的
    0.41
    Your
    0.40
    KC
    0.40
    ティア
    0.40
    ⺆
    0.40
     Your
    0.39
    Tesla
    0.38
    您的
    0.37
    扯
    0.37
    用户的
    0.37
    Act Density 0.001%

    No Known Activations