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

    Neuronpedia

    INDEX
    Explanations

    explanation or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wirkung
    0.50
     Nutzen
    0.46
     Tickets
    0.44
     markt
    0.44
     MEETING
    0.43
     Markt
    0.42
    эф
    0.42
     தன்
    0.42
    孃
    0.41
     Martínez
    0.41
    POSITIVE LOGITS
    reas
    0.56
    </u>
    0.50
    au
    0.49
    ake
    0.48
    </h4>
    0.46
    </sup>
    0.46
    ier
    0.46
    摁
    0.45
     selecion
    0.44
    </blockquote>
    0.43
    Act Density 0.000%

    No Known Activations