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

    Neuronpedia

    INDEX
    Explanations

    not ... but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ገ
    0.52
    George
    0.49
    ብስብ
    0.49
     каче
    0.49
     राज्य
    0.48
     우리의
    0.48
     resonate
    0.47
     సూ
    0.47
    𒊺
    0.47
     njegova
    0.46
    POSITIVE LOGITS
    s
    0.57
    ka
    0.52
    ต์
    0.47
    smile
    0.46
     Thai
    0.46
     Czech
    0.43
     baht
    0.43
     Buffer
    0.42
    v
    0.42
    fait
    0.42
    Act Density 0.001%

    No Known Activations