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

    Neuronpedia

    INDEX
    Explanations

    Cut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mana
    -0.07
    wend
    -0.07
     месте
    -0.07
    MASK
    -0.07
     अक
    -0.07
    max
    -0.07
    label
    -0.06
     Reservation
    -0.06
    nama
    -0.06
    中
    -0.06
    POSITIVE LOGITS
    semantic
    0.06
     čist
    0.06
     certify
    0.06
     세
    0.06
    卫生
    0.06
    ้าพ
    0.06
    ainless
    0.06
     февра
    0.05
    .into
    0.05
    ="\
    0.05
    Act Density 0.000%

    No Known Activations