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

    Neuronpedia

    INDEX
    Explanations

    **Databases:**, **Scripting/Automation:**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AZIONE
    0.40
     шы
    0.38
     adored
    0.38
    Modulo
    0.37
    ју
    0.36
    шина
    0.36
     dearly
    0.35
    ерт
    0.35
    jeto
    0.35
     چیر
    0.35
    POSITIVE LOGITS
    ափ
    0.39
     এগুলো
    0.37
     грошы
    0.37
    噸
    0.37
     বিভিন্ন
    0.36
    一篇
    0.36
     demographic
    0.36
     PSC
    0.35
     গুজ
    0.35
     nút
    0.35
    Act Density 0.000%

    No Known Activations