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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    之情
    -0.07
    脑海中
    -0.07
    _roles
    -0.07
    三分之一
    -0.07
    Compat
    -0.07
    帝王
    -0.07
    🚪
    -0.07
     đấu
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Хот
    0.07
    Marvel
    0.07
     pointers
    0.07
     Gemini
    0.07
     почем
    0.07
    הצע
    0.07
     producers
    0.06
    供货
    0.06
     DMA
    0.06
    RefCount
    0.06
    Act Density 0.001%

    No Known Activations