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

    Neuronpedia

    INDEX
    Explanations

    plot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shoulder
    -0.08
     --------↵
    -0.07
     الكوي
    -0.07
     customer
    -0.07
    自卑
    -0.07
    android
    -0.07
     screenHeight
    -0.07
    Pakistan
    -0.07
     timeless
    -0.07
     akş
    -0.07
    POSITIVE LOGITS
     plots
    0.08
     Circular
    0.08
    .plot
    0.07
     subsequently
    0.07
     Plot
    0.07
    𝑻
    0.07
    >Title
    0.07
    亨
    0.07
     plot
    0.07
     DIAG
    0.07
    Act Density 0.014%

    No Known Activations