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

    Neuronpedia

    INDEX
    Explanations

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çļĦä¸ĢåĪĩ
    -0.27
    èĩªæĿ¥
    -0.26
    åıijçĶŁåıĺåĮĸ
    -0.26
    apr
    -0.26
    arta
    -0.25
    IfExists
    -0.25
    èĪŀ
    -0.25
    åı¯èĥ½åıijçĶŁ
    -0.25
    aley
    -0.24
    plode
    -0.24
    POSITIVE LOGITS
    çĶ¸
    0.30
    Mixin
    0.27
    æ²»æĦĪ
    0.25
    身
    0.24
    ä½ĵæ£Ģ
    0.24
    ikan
    0.24
    esting
    0.24
     darkness
    0.24
     Rou
    0.24
    ä¼ijåģĩ
    0.24
    Act Density 0.000%

    No Known Activations