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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pg
    -0.06
     Mos
    -0.06
    58
    -0.06
     mohou
    -0.06
    ‌خ
    -0.06
    tx
    -0.06
    (Intent
    -0.06
    .sleep
    -0.06
    .branch
    -0.06
    .""
    -0.06
    POSITIVE LOGITS
     blocker
    0.07
     Limit
    0.07
     vaginal
    0.07
    атора
    0.06
     النس
    0.06
     اطلاعات
    0.06
    ancies
    0.06
     inhibitor
    0.06
    +B
    0.06
     nationwide
    0.06
    Act Density 0.063%

    No Known Activations