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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َو
    -0.07
    ]"
    -0.07
     vagy
    -0.06
     contradict
    -0.06
     CWE
    -0.06
     incentives
    -0.06
     Reflection
    -0.06
     высок
    -0.06
     Been
    -0.06
     mr
    -0.06
    POSITIVE LOGITS
     Shanghai
    0.08
    บาย
    0.07
     showAlert
    0.07
    iek
    0.07
    خ
    0.06
     Zag
    0.06
    anghai
    0.06
    inz
    0.06
    晴
    0.06
    logue
    0.06
    Act Density 0.000%

    No Known Activations