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

    Neuronpedia

    INDEX
    Explanations

    illegal/harmful activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     声
    -0.06
     kayı
    -0.06
     Mer
    -0.06
     مراج
    -0.06
     Architecture
    -0.06
    PY
    -0.06
    munition
    -0.06
     rept
    -0.06
    ジェ
    -0.06
     пор
    -0.06
    POSITIVE LOGITS
    周年
    0.08
    _channel
    0.07
    cci
    0.07
     istediğiniz
    0.06
     baş
    0.06
    ][-
    0.06
     ive
    0.06
     yog
    0.06
    HomeAsUp
    0.06
     Digest
    0.06
    Act Density 0.052%

    No Known Activations