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

    Neuronpedia

    INDEX
    Explanations

    references to specific superhero films and their characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    titles of books or movies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.38
     otomatig
    -0.37
    خواندن
    -0.37
     auroit
    -0.37
     kolon
    -0.36
     méda
    -0.36
     Krom
    -0.35
    CodedInputStream
    -0.35
    xmlhttp
    -0.35
    belec
    -0.35
    POSITIVE LOGITS
     surla
    0.71
     Endgame
    0.65
     فريبيس
    0.60
     Thanos
    0.57
    printStackTrace
    0.55
    ună
    0.54
    хьтан
    0.53
     насељу
    0.53
    setVerticalGroup
    0.50
    PYX
    0.50
    Act Density 0.009%

    No Known Activations