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

    Neuronpedia

    INDEX
    Explanations

    US state abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -inch
    -0.07
     Bett
    -0.07
    rench
    -0.06
    (custom
    -0.06
     onları
    -0.06
     Educ
    -0.06
    ์ค
    -0.06
    yum
    -0.06
     trench
    -0.06
     STOCK
    -0.06
    POSITIVE LOGITS
    子
    0.07
    QS
    0.07
     NSW
    0.06
    ứa
    0.06
     CI
    0.06
    December
    0.06
    JAVA
    0.06
     إن
    0.06
    환
    0.06
     MS
    0.06
    Act Density 0.012%

    No Known Activations