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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ൊന്നും
    0.74
     হ্
    0.73
     కాని
    0.67
    <unused2149>
    0.65
    <unused2130>
    0.65
    యత్
    0.62
    なくて
    0.59
    <unused2213>
    0.59
     =~
    0.59
     -*-
    0.58
    POSITIVE LOGITS
    ,
    3.62
    ،
    2.77
    !,
    2.35
    -,
    2.29
    ，
    2.27
    (),
    2.27
    ™,
    2.26
    ®,
    2.23
     ,
    2.21
    ፣
    2.18
    Act Density 0.180%

    No Known Activations