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

    Neuronpedia

    INDEX
    Explanations

    amount of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rekening
    0.50
    шенные
    0.48
    راط
    0.48
     barter
    0.48
    Spice
    0.47
    esy
    0.46
     basta
    0.45
    瓜
    0.45
    דר
    0.44
    -'+
    0.44
    POSITIVE LOGITS
     This
    0.49
     ()
    0.49
    photos
    0.47
     هذا
    0.46
     فهو
    0.45
    holder
    0.45
     ahuv
    0.44
     नेट
    0.43
    isa
    0.43
     および
    0.43
    Act Density 0.000%

    No Known Activations