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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ẑ
    -0.10
     complication
    -0.08
     ToString
    -0.08
     Target
    -0.07
     Kr
    -0.07
    ôt
    -0.07
    coder
    -0.07
    込め
    -0.07
     Ross
    -0.07
     deste
    -0.07
    POSITIVE LOGITS
     outbound
    0.07
    YSQL
    0.07
    办
    0.07
     Aub
    0.06
    엜
    0.06
    SHA
    0.06
    ﯯ
    0.06
    _counters
    0.06
     chiff
    0.06
     weblog
    0.06
    Act Density 0.002%

    No Known Activations