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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    now
    -0.07
    eten
    -0.06
     cubes
    -0.06
     crossAxisAlignment
    -0.06
     bots
    -0.06
     Distance
    -0.06
    DOG
    -0.06
    eyes
    -0.06
    曰
    -0.06
    Single
    -0.06
    POSITIVE LOGITS
    iễn
    0.07
     hư
    0.07
    titre
    0.07
    ้อง
    0.07
     акку
    0.07
     --------------------------------------------------------------------------↵
    0.06
     نیروی
    0.06
     harass
    0.06
     lịch
    0.06
    ็จ
    0.06
    Act Density 0.011%

    No Known Activations