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

    Neuronpedia

    INDEX
    Explanations

    southwest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auroit
    -1.04
     feroit
    -0.98
     Efq
    -0.97
     avoient
    -0.96
     Majefty
    -0.96
     étoit
    -0.94
     étoient
    -0.94
     myſelf
    -0.93
     sfeer
    -0.92
     Landscape
    -0.91
    POSITIVE LOGITS
     As
    0.52
    tk
    0.49
     Sel
    0.48
     De
    0.47
     Sa
    0.47
     MotionEvent
    0.46
     issue
    0.46
    <bos>
    0.45
     A
    0.44
     af
    0.44
    Act Density 0.068%

    No Known Activations