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

    Neuronpedia

    INDEX
    Explanations

    validate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蓝天
    -0.07
    德
    -0.07
    ㏓
    -0.07
     Same
    -0.06
    onomous
    -0.06
    lients
    -0.06
     năng
    -0.06
     Strange
    -0.06
    pler
    -0.06
    -S
    -0.06
    POSITIVE LOGITS
    ,
    0.09
    INCLUDE
    0.07
    .Fatal
    0.07
    mıştır
    0.07
     prefixes
    0.07
    赒
    0.07
    复制
    0.06
    כרטיס
    0.06
     woven
    0.06
     hesitate
    0.06
    Act Density 0.172%

    No Known Activations