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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ream
    -0.30
    escription
    -0.28
     Glo
    -0.25
    主管
    -0.25
    ixmap
    -0.24
    注åħ¥
    -0.24
     -------------------------------------------------------------------------↵
    -0.24
    主åħ¬
    -0.24
    çī¹æľĹ
    -0.24
    Injected
    -0.24
    POSITIVE LOGITS
    æľº
    0.26
    jni
    0.26
    ey
    0.26
    åĬŁèĥ½æĢ§
    0.26
    ÑĩÑĮ
    0.25
    åĮºåĿĹéĵ¾
    0.25
    åIJĪ
    0.25
    ç»ĵ
    0.24
    ise
    0.24
    eyJ
    0.24
    Act Density 0.772%

    No Known Activations