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

    Neuronpedia

    INDEX
    Explanations

    dmesg tail or batch size samples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kir
    0.46
     প্রভাস
    0.44
     Dru
    0.43
     Salam
    0.43
     Qar
    0.43
     Bak
    0.42
     Drupal
    0.41
     Klaus
    0.41
     быть
    0.41
     отре
    0.40
    POSITIVE LOGITS
    ಣ
    0.47
     discerning
    0.46
    用户
    0.45
    plated
    0.45
    水中
    0.44
    衣
    0.43
    水
    0.43
    மண
    0.41
    পত্র
    0.41
    াজা
    0.41
    Act Density 0.000%

    No Known Activations