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

    Neuronpedia

    INDEX
    Explanations

    calories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ensure
    -0.07
    .top
    -0.07
    起飞
    -0.07
     הת
    -0.07
    cfg
    -0.07
    常态化
    -0.07
    �
    -0.07
     widespread
    -0.07
    support
    -0.07
     süreç
    -0.06
    POSITIVE LOGITS
    闿
    0.08
     calories
    0.08
    빪
    0.08
    téri
    0.08
    pełni
    0.07
     가지
    0.07
     Penalty
    0.07
     electro
    0.07
    のか
    0.07
    apatkan
    0.07
    Act Density 0.002%

    No Known Activations