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

    Neuronpedia

    INDEX
    Explanations

    lat/len

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lin
    -1.08
    lon
    -1.04
    lat
    -0.95
    lar
    -0.91
    len
    -0.86
    lor
    -0.79
    link
    -0.75
    length
    -0.72
    lone
    -0.68
    las
    -0.66
    POSITIVE LOGITS
     MainAxisSize
    0.91
     myſelf
    0.88
     BoxFit
    0.88
    fjspx
    0.87
     themſelves
    0.87
     Majefty
    0.85
     greateſt
    0.83
     becauſe
    0.82
     purpoſe
    0.81
     photolibrary
    0.80
    Act Density 0.076%

    No Known Activations