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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     actual
    -0.33
    å®ŀéĻħ
    -0.29
    rics
    -0.29
    æīģ
    -0.28
    BED
    -0.28
    å®ŀéĻħä¸Ĭ
    -0.28
    actual
    -0.27
    ündig
    -0.27
     actually
    -0.27
    许å¤ļ
    -0.27
    POSITIVE LOGITS
    icos
    0.29
    ikon
    0.27
    iko
    0.26
    iveau
    0.25
    ico
    0.25
     kali
    0.24
    讣
    0.23
    æľīæľŁ
    0.23
    æĪĺåľºä¸Ĭ
    0.23
    人éĻħåħ³ç³»
    0.23
    Act Density 0.018%

    No Known Activations