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

    Neuronpedia

    INDEX
    Explanations

    git reset --hard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Myths
    0.46
     ballads
    0.45
    ៥
    0.42
     전망
    0.42
    पूजा
    0.42
     소재
    0.42
    ?/
    0.42
     황
    0.41
    किला
    0.40
    ផ្សេង
    0.40
    POSITIVE LOGITS
     integer
    0.61
     boolean
    0.61
     values
    0.59
     concatenated
    0.58
     parameterized
    0.58
     iterable
    0.57
     value
    0.57
     iterator
    0.55
     parsed
    0.55
     predefined
    0.55
    Act Density 2.290%

    No Known Activations