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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SMB
    -0.07
     כל
    -0.07
    稚
    -0.07
     Tail
    -0.07
     gì
    -0.07
    瑞典
    -0.07
     anything
    -0.07
     atenção
    -0.07
    ݬ
    -0.07
     fís
    -0.06
    POSITIVE LOGITS
    olars
    0.08
    >-->↵
    0.07
     רי
    0.07
    媞
    0.07
    oller
    0.07
    .Charting
    0.07
     independently
    0.07
    (records
    0.07
    �
    0.06
     Instantiate
    0.06
    Act Density 0.002%

    No Known Activations