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

    Neuronpedia

    INDEX
    Explanations

    find help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المملكة
    0.87
    കം
    0.84
     slalom
    0.78
    Pos
    0.72
    gesamt
    0.70
    owels
    0.70
    ampionship
    0.70
    izantes
    0.70
    ทยาลัย
    0.70
    गात
    0.69
    POSITIVE LOGITS
    emed
    0.87
    Interact
    0.79
     Input
    0.76
    互動
    0.75
     ause
    0.73
     Interact
    0.72
    Interaction
    0.71
     usare
    0.69
     Outreach
    0.69
     käyttää
    0.69
    Act Density 0.021%

    No Known Activations