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
     DATA
    -0.06
     attacks
    -0.06
     answer
    -0.06
     computational
    -0.06
     consequences
    -0.06
     مطالعه
    -0.06
     sis
    -0.06
    ايش
    -0.06
    icontains
    -0.06
    \controllers
    -0.06
    POSITIVE LOGITS
    -ln
    0.07
     Improved
    0.06
    localctx
    0.06
    ород
    0.06
    .dk
    0.06
    ("@
    0.06
    Summary
    0.06
     lesbian
    0.06
     puesto
    0.06
    petto
    0.06
    Act Density 0.012%

    No Known Activations