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

    Neuronpedia

    INDEX
    Explanations

    list items or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사람
    0.40
    ငံ
    0.39
    Prototype
    0.39
    涯
    0.38
     pluripotent
    0.37
    ➎
    0.37
    ارين
    0.37
     нәрсә
    0.37
    থমে
    0.37
     شما
    0.37
    POSITIVE LOGITS
    ↵
    0.66
    ↵↵
    0.59
     Moreover
    0.53
     ,
    0.53
     and
    0.48
     Similarly
    0.45
    and
    0.43
    ica
    0.41
    io
    0.41
    Moreover
    0.40
    Act Density 0.264%

    No Known Activations