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

    Neuronpedia

    INDEX
    Explanations

    based on calibration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caballo
    0.45
     bebé
    0.41
    lastname
    0.41
    াস্থ্যের
    0.41
    ্া
    0.40
     நடிக
    0.40
    ാവുന്ന
    0.40
    ત્
    0.40
    apellido
    0.39
    вален
    0.38
    POSITIVE LOGITS
     інших
    0.60
     अन्य
    0.50
    其他
    0.50
    Autres
    0.50
     autres
    0.48
    或其他
    0.48
     иных
    0.48
     અન્ય
    0.48
     Purchases
    0.45
     других
    0.45
    Act Density 0.003%

    No Known Activations