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

    Neuronpedia

    INDEX
    Explanations

    connecting words and pronouns in political and musical contexts, especially in longer phrases

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĸ°çļĦ
    -0.10
     new
    -0.07
    alker
    -0.07
    WithMany
    -0.07
    auss
    -0.06
    ystems
    -0.06
     اÙĦجدÙĬد
    -0.06
    =new
    -0.06
     anew
    -0.06
    546
    -0.06
    POSITIVE LOGITS
     attempted
    0.11
     brief
    0.10
     attempt
    0.09
     briefly
    0.09
     attempts
    0.09
     Brief
    0.09
     failed
    0.09
     abort
    0.09
     early
    0.09
    Attempt
    0.09
    Act Density 0.041%

    No Known Activations