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

    Neuronpedia

    INDEX
    Explanations

    comparison of two or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     免
    0.39
    klär
    0.39
     면
    0.36
     swab
    0.36
    همه
    0.36
     নামকরণ
    0.36
    保险
    0.35
     პირადი
    0.35
     Pemer
    0.34
     Executes
    0.34
    POSITIVE LOGITS
    断
    0.42
     braiding
    0.40
     Эль
    0.39
     retreating
    0.37
     distant
    0.36
     interrupting
    0.36
    angor
    0.36
    axies
    0.35
    Melissa
    0.35
    })=
    0.35
    Act Density 0.007%

    No Known Activations