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

    Neuronpedia

    INDEX
    Explanations

    describing old things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.50
     enthous
    0.48
     полиции
    0.48
    ቶ
    0.46
    ન
    0.46
    ټر
    0.46
     ಅಂ
    0.45
     Accountability
    0.45
    当日
    0.45
     Policía
    0.45
    POSITIVE LOGITS
     she
    0.54
     sewing
    0.47
     he
    0.46
     okay
    0.45
    estion
    0.44
    Designer
    0.44
     co
    0.44
     woodworking
    0.44
     delving
    0.44
     vampire
    0.43
    Act Density 0.000%

    No Known Activations