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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    范
    -0.08
    楝
    -0.08
    迪士
    -0.07
    ◅
    -0.07
    )↵↵↵↵↵↵↵↵
    -0.07
    찡
    -0.07
     onItemClick
    -0.07
    �
    -0.07
    @show
    -0.07
     invert
    -0.07
    POSITIVE LOGITS
     followers
    0.07
    טרה
    0.07
     Logic
    0.07
     .....
    0.07
    upper
    0.07
     talking
    0.07
    numero
    0.07
    vara
    0.07
     Shar
    0.07
     Assass
    0.07
    Act Density 0.021%

    No Known Activations