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

    Neuronpedia

    INDEX
    Explanations

    supervision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AGR
    -0.30
    ês
    -0.27
    æĬĬèĩªå·±çļĦ
    -0.26
    Ñģли
    -0.25
     зам
    -0.25
    å°ijäºĨ
    -0.25
    å°Ĩèĩªå·±çļĦ
    -0.24
    è¾ĸ
    -0.24
    åİĭåĪ¶
    -0.24
     chrom
    -0.24
    POSITIVE LOGITS
    -touch
    0.27
    xf
    0.26
    licit
    0.26
    Human
    0.25
    vant
    0.25
    icit
    0.24
    便åĪ©
    0.24
    oven
    0.24
    æ¿Ģ
    0.24
    appable
    0.23
    Act Density 0.006%

    No Known Activations