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

    Neuronpedia

    INDEX
    Explanations

    void

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    よ
    -0.08
    (__
    -0.07
     limite
    -0.07
     다만
    -0.07
    取决于
    -0.07
     battles
    -0.07
    管理制度
    -0.07
     supplement
    -0.07
    patches
    -0.07
     Guidelines
    -0.06
    POSITIVE LOGITS
     withRouter
    0.07
    getClass
    0.07
     DIS
    0.07
    -fired
    0.07
    榑
    0.07
    宅
    0.07
    兒童
    0.06
    ✰
    0.06
     fluoride
    0.06
    (undefined
    0.06
    Act Density 0.016%

    No Known Activations