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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĮ½
    -0.33
    oge
    -0.28
     obsc
    -0.28
    озд
    -0.28
    encer
    -0.26
     proport
    -0.25
    angu
    -0.25
    OfClass
    -0.25
     constitutional
    -0.24
    ä¸įæĪIJ
    -0.24
    POSITIVE LOGITS
    主ä¸ļ
    0.27
    å¤Ħ
    0.26
    åĨ¯
    0.26
    æī¾äºĨ
    0.25
    ä¸ļ绩
    0.25
    bei
    0.25
    Logger
    0.24
    主线
    0.24
    è§ĨåĬĽ
    0.24
    rex
    0.24
    Act Density 0.666%

    No Known Activations