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

    Neuronpedia

    INDEX
    Explanations

    goals and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    having
    0.22
     Having
    0.19
    Having
    0.19
    '
    0.18
    ↵
    0.17
    être
    0.17
     Being
    0.17
    ishments
    0.17
     adanya
    0.17
     ;
    0.17
    POSITIVE LOGITS
     creating
    0.39
     achieving
    0.35
     assessing
    0.34
     improving
    0.33
     securing
    0.33
     furthering
    0.33
     capturing
    0.33
     maximizing
    0.32
     preserving
    0.32
     attaining
    0.32
    Act Density 0.286%

    No Known Activations