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

    Neuronpedia

    INDEX
    Explanations

    picking favorites and notable examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spaceship
    0.42
     چنان
    0.41
    eyeglasses
    0.38
    FindingsResponse
    0.38
    persona
    0.38
    eways
    0.37
     quelconque
    0.36
    ievements
    0.36
     جیسا
    0.36
     справа
    0.36
    POSITIVE LOGITS
     ones
    0.89
     newer
    0.80
     entrants
    0.80
     contenders
    0.79
     favorites
    0.78
     favourites
    0.74
     quelli
    0.70
     candidates
    0.70
     entries
    0.69
     guys
    0.69
    Act Density 0.106%

    No Known Activations