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

    Neuronpedia

    INDEX
    Explanations

    entering into states or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     አገልግሎ
    0.40
    <unused20>
    0.37
    ကြည့်
    0.36
    が通販
    0.35
    ᱐
    0.35
     استخدم
    0.35
    kfollowers
    0.35
     своїх
    0.35
    <unused1134>
    0.33
    itudine
    0.33
    POSITIVE LOGITS
     of
    0.59
    0.59
     on
    0.53
     by
    0.52
     is
    0.51
     was
    0.51
     and
    0.50
    w
    0.49
     an
    0.49
     to
    0.46
    Act Density 0.857%

    No Known Activations