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

    Neuronpedia

    INDEX
    Explanations

    as the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eventually
    0.18
    “,
    0.17
    “.
    0.17
     সুযোগ
    0.16
     সাধারণত
    0.16
    倌
    0.16
     നല്‍
    0.15
    QPushButton
    0.15
    ="",
    0.15
    rekken
    0.15
    POSITIVE LOGITS
     എന്നിവ
    0.22
    도
    0.21
    ת
    0.20
     ஆகியோர்
    0.20
     ஆகிய
    0.19
     are
    0.19
     ک
    0.18
     ஆகியவற்ற
    0.18
     serta
    0.18
    과
    0.17
    Act Density 0.161%

    No Known Activations