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

    Neuronpedia

    INDEX
    Explanations

    patterns or repeated sequences in the text

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

    code structure and diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.54
    StructEnd
    -0.52
    Syst
    -0.50
    wixt
    -0.50
     vitt
    -0.46
     fluo
    -0.46
    Pug
    -0.46
     Exploit
    -0.46
     اخت
    -0.46
     Stitch
    -0.45
    POSITIVE LOGITS
    océan
    0.58
     Bewußt
    0.54
     Entste
    0.54
     zijne
    0.53
     mães
    0.52
     corações
    0.50
     werkzaam
    0.50
     temprana
    0.49
    ніципа
    0.48
     pemimpin
    0.48
    Act Density 0.025%

    No Known Activations