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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhyth
    -0.07
     за
    -0.07
    ategy
    -0.07
     Emp
    -0.07
     המצ
    -0.06
    Psych
    -0.06
    😜
    -0.06
    juries
    -0.06
    模糊
    -0.06
     safeguards
    -0.06
    POSITIVE LOGITS
    华尔
    0.08
    在其
    0.07
    把这些
    0.07
     Edwards
    0.07
     יעקב
    0.07
     slavery
    0.07
     Uploaded
    0.06
     Takes
    0.06
     shaved
    0.06
    嘉
    0.06
    Act Density 0.037%

    No Known Activations