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

    Neuronpedia

    INDEX
    Explanations

    possessives and contractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Composition
    -0.29
     Adjustment
    -0.26
    éłħ
    -0.26
     Composition
    -0.25
    æłĩçļĦ
    -0.25
    happy
    -0.25
    çļĦåķĨåĵģ
    -0.24
    该项
    -0.24
    项
    -0.24
    Adjusted
    -0.24
    POSITIVE LOGITS
    zte
    0.29
     alph
    0.26
    ört
    0.26
     customs
    0.26
    éķ¿
    0.26
     shed
    0.25
    idden
    0.25
    竽
    0.24
    å½ĵå±Ģ
    0.24
    åľĨ
    0.24
    Act Density 3.526%

    No Known Activations