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

    Neuronpedia

    INDEX
    Explanations

    outside of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å¿ĺ
    -0.28
    çĹĩ
    -0.26
    æĻ®åıĬ
    -0.25
    ains
    -0.25
    带
    -0.25
     others
    -0.25
     tym
    -0.25
     âĨIJ
    -0.25
    æĮĩ示
    -0.25
    èĩªåĪ¶
    -0.25
    POSITIVE LOGITS
    ipur
    0.31
     camps
    0.27
    arker
    0.27
    TemplateName
    0.26
    ScreenState
    0.25
    åĬŀæ³ķ
    0.25
    -inverse
    0.25
    uito
    0.24
    eland
    0.24
     camp
    0.24
    Act Density 0.003%

    No Known Activations