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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otas
    -0.07
    แค
    -0.07
     Ý
    -0.06
    ाध
    -0.06
     Madonna
    -0.06
     gái
    -0.06
    ỗ
    -0.06
     iterate
    -0.06
     비밀글
    -0.06
     Auschwitz
    -0.06
    POSITIVE LOGITS
     Auburn
    0.06
    Approval
    0.06
    imar
    0.06
     hur
    0.06
     багат
    0.06
    /csv
    0.06
     procedural
    0.06
     auditing
    0.06
     قر
    0.06
     Legislation
    0.05
    Act Density 0.000%

    No Known Activations