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

    Neuronpedia

    INDEX
    Explanations

    code/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    委
    -0.07
     crappy
    -0.06
     shitty
    -0.06
     Gad
    -0.06
     Fault
    -0.06
    282
    -0.06
     दर
    -0.06
     ALSO
    -0.06
     Dere
    -0.06
     fault
    -0.06
    POSITIVE LOGITS
     tươi
    0.07
    Exchange
    0.07
    블
    0.07
    치는
    0.07
    ميم
    0.07
     SMTP
    0.06
    Codec
    0.06
    SVG
    0.06
    К
    0.06
     inertia
    0.06
    Act Density 0.004%

    No Known Activations