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

    Neuronpedia

    INDEX
    Explanations

    deaths and murders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regret
    -0.07
     Denn
    -0.06
    ....↵↵
    -0.06
    (mp
    -0.06
    UnitTest
    -0.06
    iд
    -0.06
     зап
    -0.06
    دار
    -0.06
     gard
    -0.06
    ,null
    -0.06
    POSITIVE LOGITS
     BTN
    0.07
    ingle
    0.07
    Jets
    0.07
     Babylon
    0.06
    codec
    0.06
     sitesi
    0.06
     محمود
    0.06
     fclose
    0.06
     achievable
    0.06
    迪
    0.06
    Act Density 0.071%

    No Known Activations