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

    Neuronpedia

    INDEX
    Explanations

    Ordinal numbers suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ankles
    -0.07
     плю
    -0.06
     nejen
    -0.06
    高清
    -0.06
     neutral
    -0.06
     integers
    -0.06
    .indices
    -0.06
     pornography
    -0.06
    apor
    -0.06
    strconv
    -0.06
    POSITIVE LOGITS
    st
    0.10
    ST
    0.09
    std
    0.07
     THIRD
    0.07
     Kunst
    0.07
    th
    0.07
     ↑
    0.07
    ±ظ
    0.07
    Fourth
    0.07
     Fourth
    0.07
    Act Density 0.029%

    No Known Activations