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

    Neuronpedia

    INDEX
    Explanations

    void followed by Main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ent
    0.44
    doesn
    0.42
    erings
    0.41
    ologisk
    0.41
    el
    0.40
    whelming
    0.40
    höhe
    0.40
    områ
    0.39
    acchar
    0.39
    os
    0.38
    POSITIVE LOGITS
     enqueue
    0.45
     execute
    0.44
     initialize
    0.42
     allocate
    0.39
     add
    0.39
     calculate
    0.38
     analyze
    0.38
     audition
    0.38
     slew
    0.37
     goTo
    0.37
    Act Density 0.033%

    No Known Activations