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

    Neuronpedia

    INDEX
    Explanations

    fork lift, array, running

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ..?
    0.47
     sre
    0.42
    महाराष्ट
    0.42
    ?..
    0.42
    杍
    0.41
     lorsqu
    0.40
     hvis
    0.40
     राजू
    0.40
     لص
    0.39
     aisl
    0.39
    POSITIVE LOGITS
    Array
    0.37
    Note
    0.37
    note
    0.37
    Fa
    0.36
     rents
    0.36
     mi
    0.35
    Fisher
    0.35
    Anime
    0.35
    uzzy
    0.35
    しま
    0.34
    Act Density 0.000%

    No Known Activations