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

    Neuronpedia

    INDEX
    Explanations

    placeholders and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᧐
    0.46
     (‘
    0.40
    ߋ
    0.37
     (“
    0.37
     (’
    0.36
     ("
    0.36
     ('
    0.35
     ():
    0.35
     (`
    0.33
    ုန်
    0.33
    POSITIVE LOGITS
    here
    0.59
     aqui
    0.58
     Aqui
    0.55
    ListOf
    0.55
     εδώ
    0.55
     هنا
    0.54
    }=(
    0.54
     here
    0.54
     இங்கு
    0.54
     tutaj
    0.54
    Act Density 0.109%

    No Known Activations