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

    Neuronpedia

    INDEX
    Explanations

    code strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (',')[
    -0.07
     alacak
    -0.06
     comply
    -0.06
    _MSK
    -0.06
    _Word
    -0.06
    .FILE
    -0.06
    cheduled
    -0.06
     correlate
    -0.06
     القرآن
    -0.06
     Io
    -0.06
    POSITIVE LOGITS
    �能
    0.07
     ड
    0.06
     现
    0.06
    ain
    0.06
    -after
    0.06
     zby
    0.06
    .station
    0.06
    ımızın
    0.06
    ΙΣ
    0.06
     arc
    0.06
    Act Density 0.066%

    No Known Activations