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

    Neuronpedia

    INDEX
    Explanations

    number followed by options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     influencers
    0.38
     اہمیت
    0.36
     infrast
    0.36
     trasmissione
    0.36
     institutions
    0.35
     infrastrukt
    0.35
     multipliers
    0.34
     learnings
    0.34
     professions
    0.33
     heuristics
    0.33
    POSITIVE LOGITS
    7
    0.53
    6
    0.51
    8
    0.48
    9
    0.47
    .
    0.45
    4
    0.45
    2
    0.44
    :
    0.40
    and
    0.40
    or
    0.40
    Act Density 0.065%

    No Known Activations