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

    Neuronpedia

    INDEX
    Explanations

    ganz vil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ጧ
    0.46
    Ბ
    0.41
     ৩৮
    0.40
    𝗪
    0.40
    เยี่ยม
    0.39
    ="@+
    0.39
    𝜋
    0.39
    ኀ
    0.38
    ￭
    0.38
    𝗮
    0.38
    POSITIVE LOGITS
     وچ
    0.85
     บ่
    0.81
     ኣ
    0.77
     एगो
    0.77
     تے
    0.74
    佢
    0.72
     vun
    0.71
    ဍ
    0.71
     ኣብ
    0.68
    嗰
    0.65
    Act Density 0.005%

    No Known Activations