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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to bugs and software development

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

    Godzilla monsters VS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rshire
    -0.45
     specialise
    -0.44
    cashire
    -0.42
     sown
    -0.40
     specialised
    -0.39
     trigo
    -0.38
     młod
    -0.38
     chré
    -0.37
    FromNib
    -0.36
    glises
    -0.36
    POSITIVE LOGITS
     Godzilla
    2.14
    Godzilla
    1.98
    zilla
    1.54
    ジラ
    0.73
     monstre
    0.59
     monsters
    0.58
     monster
    0.56
     monstru
    0.56
     godz
    0.55
    AndEndTag
    0.54
    Act Density 0.001%

    No Known Activations