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

    Neuronpedia

    INDEX
    Explanations

    concepts related to evidence and assessment in a systematic context

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    measurements involving complexes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saken
    -0.31
    HasAnnotation
    -0.28
    findpost
    -0.27
     Obtenez
    -0.26
     förb
    -0.25
    期刊论文
    -0.24
     desselben
    -0.24
     společnost
    -0.24
     trône
    -0.24
     varandra
    -0.24
    POSITIVE LOGITS
    OGND
    0.80
     autorytatywna
    0.74
    rungsseite
    0.69
     ſeines
    0.68
    <pad>
    0.68
     パンチラ
    0.68
    <unused68>
    0.67
    <unused17>
    0.67
    [@BOS@]
    0.67
    <unused8>
    0.67
    Act Density 0.742%

    No Known Activations