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

    Neuronpedia

    INDEX
    Explanations

    names and foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ꯠ
    0.43
     Talend
    0.43
     tara
    0.42
     Tao
    0.42
    妫
    0.41
    বাগ
    0.40
     Bento
    0.39
     Bamberg
    0.38
    Visiting
    0.38
     Banerjee
    0.37
    POSITIVE LOGITS
    ማ
    0.35
    Alex
    0.34
     queridos
    0.32
    lex
    0.32
    hod
    0.32
     Marilyn
    0.32
     Alex
    0.32
     ци
    0.31
    ได
    0.31
    cinn
    0.31
    Act Density 0.012%

    No Known Activations