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

    Neuronpedia

    INDEX
    Explanations

    region

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åĮºåŁŁ
    -0.27
     Yö
    -0.26
    ipl
    -0.26
    ipel
    -0.26
    å»Ĭ
    -0.24
    ihan
    -0.24
    åįĢåŁŁ
    -0.24
    æŁ¬
    -0.24
    etr
    -0.24
    åļı
    -0.24
    POSITIVE LOGITS
    _msgs
    0.27
     scratching
    0.25
     Premium
    0.25
    ê²°
    0.25
    Premium
    0.25
     premium
    0.25
    acea
    0.24
    æľªå©ļ
    0.24
    iese
    0.23
    è¦ı
    0.23
    Act Density 2.973%

    No Known Activations