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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATORS
    -0.07
     Buzz
    -0.07
    ustum
    -0.07
    Tap
    -0.07
    DIM
    -0.06
    ingles
    -0.06
    -dist
    -0.06
    TLS
    -0.06
     aspirations
    -0.06
    Equals
    -0.06
    POSITIVE LOGITS
    �
    0.08
     sesso
    0.06
    ernal
    0.06
     coating
    0.06
     seria
    0.06
     المن
    0.06
     року
    0.06
     Ninh
    0.06
    .coordinate
    0.06
    -num
    0.06
    Act Density 0.014%

    No Known Activations