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

    Neuronpedia

    INDEX
    Explanations

    Setting: interactive game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ，
    0.38
    0.37
     ''){
    0.34
     ٣
    0.34
     û
    0.33
     tất
    0.32
     على
    0.32
    ,((
    0.32
     ؛
    0.32
     (’
    0.32
    POSITIVE LOGITS
    ли
    0.50
    ق
    0.47
    ہ
    0.46
     and
    0.46
    ע
    0.45
    IO
    0.43
    Y
    0.43
    ید
    0.42
    ed
    0.41
    h
    0.41
    Act Density 0.000%

    No Known Activations