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

    Neuronpedia

    INDEX
    Explanations

    special characters and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     welcoming
    0.43
    dp
    0.41
     swept
    0.40
    கூ
    0.40
     প্রত্যা
    0.39
     SPMs
    0.39
     sticks
    0.38
    ឆ្ល
    0.38
     muff
    0.38
     treasured
    0.38
    POSITIVE LOGITS
     ctrl
    0.43
     Capricorn
    0.41
     Ctrl
    0.40
    tais
    0.39
     zen
    0.39
     զ
    0.39
     serie
    0.39
     Series
    0.38
     Serie
    0.38
     Qué
    0.38
    Act Density 0.000%

    No Known Activations