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

    Neuronpedia

    INDEX
    Explanations

    Diagrams and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    電子信箱
    -0.07
    <O
    -0.07
     baff
    -0.07
    ден
    -0.07
    меди
    -0.06
    FK
    -0.06
    洗脸
    -0.06
    =max
    -0.06
    ₡
    -0.06
    DXVECTOR
    -0.06
    POSITIVE LOGITS
    станавлива
    0.07
     riêng
    0.07
     bola
    0.07
                    ↵
    0.07
     &,
    0.06
     *)&
    0.06
    _exe
    0.06
    0.06
    0.06
    なか
    0.06
    Act Density 0.002%

    No Known Activations