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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases and structured elements in a document

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

    listing numbers and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.77
    Personendaten
    -0.70
    曖昧さ回避
    -0.68
    +#+
    -0.67
    InitVars
    -0.66
    GEBURTSDATUM
    -0.65
    MessageOf
    -0.63
    -0.59
     témoig
    -0.59
     الرياضيه
    -0.59
    POSITIVE LOGITS
    hat
    0.27
    stufe
    0.26
    ":[{
    0.26
     vâ
    0.24
    räge
    0.24
    into
    0.23
    oche
    0.23
     exquisite
    0.23
     picada
    0.23
     senso
    0.23
    Act Density 0.383%

    No Known Activations