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

    Neuronpedia

    INDEX
    Explanations

    artist names and handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     determination
    0.45
     symbols
    0.42
     Symbols
    0.41
    Squirrel
    0.40
    回避
    0.39
     determinations
    0.38
     Scarlett
    0.38
     Scarlet
    0.37
     kaç
    0.37
    Determination
    0.37
    POSITIVE LOGITS
    名前
    0.54
    name
    0.51
    ชื่อ
    0.50
     nombre
    0.49
     이름
    0.48
    nombre
    0.47
    名字
    0.47
     이름을
    0.46
    lname
    0.46
    名を
    0.45
    Act Density 0.007%

    No Known Activations