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

    Neuronpedia

    INDEX
    Explanations

    programming main function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (_
    0.54
     (*)
    0.51
    (_
    0.50
     (*
    0.50
     _
    0.50
    ()->
    0.48
    ():
    0.48
    (*)
    0.46
    0.45
    (*
    0.44
    POSITIVE LOGITS
     PACE
    0.45
     veramente
    0.43
    িতেছে
    0.42
    <unused44>
    0.40
    ;",
    0.39
     সোভিয়েত
    0.39
    িল
    0.38
    $[
    0.38
    য়েক
    0.37
    aeskeygenassist
    0.37
    Act Density 0.001%

    No Known Activations