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

    Neuronpedia

    INDEX
    Explanations

    already exists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不出
    0.68
     intricately
    0.68
    いき
    0.67
     stamping
    0.64
     remnants
    0.64
    stays
    0.64
     revital
    0.64
     ingen
    0.63
     involvement
    0.63
     everything
    0.63
    POSITIVE LOGITS
     esist
    0.90
     Уже
    0.82
    exists
    0.81
    ړي
    0.81
     Already
    0.78
    ∃
    0.76
     bestaan
    0.76
     sbParams
    0.75
    ћа
    0.75
    unist
    0.75
    Act Density 0.307%

    No Known Activations