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

    Neuronpedia

    INDEX
    Explanations

    boat sales disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .activation
    -0.08
    汧
    -0.07
     hạt
    -0.07
    ꧈
    -0.07
    け
    -0.07
    委宣传
    -0.07
    .xr
    -0.07
     drv
    -0.07
     heirs
    -0.07
    .nav
    -0.06
    POSITIVE LOGITS
     Solar
    0.08
    bsolute
    0.08
    任務
    0.07
     Responsibility
    0.07
    的照片
    0.07
     Atmos
    0.07
    这张
    0.07
    Trail
    0.06
    stituição
    0.06
    abajo
    0.06
    Act Density 0.008%

    No Known Activations