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

    Neuronpedia

    INDEX
    Explanations

    text in languages other than English (likely Croatian and German) mixed with HTML formatting

    oai_token-act-pair · gemini-2.0-flash

    variations of "over"

    np_token-act-pair-logits · gpt-4o-mini

    ">"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -1.05
     NSCoder
    -0.94
     ―――――
    -0.91
     Мексичка
    -0.83
    
    -0.82
    ^(@)
    -0.81
    rungsseite
    -0.81
     InputDecoration
    -0.80
     Cæsar
    -0.78
    }();
    -0.77
    POSITIVE LOGITS
     prior
    0.49
     up
    0.47
     Over
    0.44
    ย
    0.43
     Bew
    0.42
     B
    0.42
     member
    0.42
     sa
    0.41
     over
    0.41
     ber
    0.41
    Act Density 0.229%

    No Known Activations