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

    Neuronpedia

    INDEX
    Explanations

    chess notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     expuls
    0.41
     pudd
    0.41
    ىر
    0.39
     Conductivity
    0.38
     strument
    0.38
     gesagt
    0.37
     Gemeins
    0.37
     obsol
    0.37
    雋
    0.36
     pudding
    0.36
    POSITIVE LOGITS
     пане
    0.39
    🤑
    0.39
    align
    0.37
     endors
    0.37
    berta
    0.35
    !?
    0.35
    renderSquare
    0.35
    endale
    0.35
    σιά
    0.35
    ongi
    0.34
    Act Density 0.001%

    No Known Activations