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

    Neuronpedia

    INDEX
    Explanations

    Encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DATABASE
    -0.07
     expression
    -0.06
     teachers
    -0.06
    -gallery
    -0.06
     matrix
    -0.06
    959
    -0.06
     CWE
    -0.06
    Explorer
    -0.06
     tanks
    -0.06
     bx
    -0.06
    POSITIVE LOGITS
    ząd
    0.07
     wird
    0.07
     Uncomment
    0.06
    gend
    0.06
    arking
    0.06
     شروع
    0.06
    으로
    0.06
    .getBytes
    0.06
    ‌اند
    0.06
    (PORT
    0.06
    Act Density 0.003%

    No Known Activations