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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pose
    -0.28
    代
    -0.27
     onActivityResult
    -0.27
    helper
    -0.26
    PS
    -0.26
     post
    -0.26
    atism
    -0.26
    odox
    -0.25
    post
    -0.25
    红åĮħ
    -0.24
    POSITIVE LOGITS
     interesting
    0.26
    æľī趣
    0.26
    Stamp
    0.25
     Stamp
    0.24
    rossover
    0.24
    .Inf
    0.23
     ÑģÑĭ
    0.23
    interesting
    0.23
    Dragging
    0.23
    ýt
    0.23
    Act Density 0.014%

    No Known Activations