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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %;
↵
    -0.07
    ustralia
    -0.07
     democrat
    -0.07
     לבד
    -0.06
    .GetAll
    -0.06
    �
    -0.06
    我们一起
    -0.06
    بخ
    -0.06
    ʨ
    -0.06
    ₀
    -0.06
    POSITIVE LOGITS
    _disk
    0.07
     crítica
    0.07
    iom
    0.07
    metal
    0.07
     jails
    0.07
     пара
    0.07
     rocker
    0.07
     casts
    0.07
    된다
    0.07
     kết
    0.07
    Act Density 0.184%

    No Known Activations