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

    Neuronpedia

    INDEX
    Explanations

    available to the public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     образом
    0.36
    rune
    0.36
    ruby
    0.36
    μένη
    0.35
    וק
    0.35
     rebounding
    0.35
     बेटा
    0.34
    Famous
    0.34
    ewnątrz
    0.34
     段
    0.34
    POSITIVE LOGITS
     through
    0.61
     via
    0.60
     melalui
    0.54
     thru
    0.52
     ava
    0.50
     через
    0.50
     Through
    0.49
     públic
    0.48
     til
    0.46
     available
    0.46
    Act Density 0.022%

    No Known Activations