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

    Neuronpedia

    INDEX
    Explanations

    references to brand names and product descriptions

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

    specific models and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.63
    withIdentifier
    -0.60
    Personendaten
    -0.57
    RectangleBorder
    -0.56
    expandindo
    -0.56
    TagMode
    -0.55
    httphttps
    -0.54
    UnknownFieldSet
    -0.51
    AndEndTag
    -0.51
    Бахар
    -0.50
    POSITIVE LOGITS
    ambilan
    0.42
    Baca
    0.36
    ніципа
    0.35
     telinga
    0.35
    ivotopis
    0.35
     rayos
    0.34
     fallecido
    0.33
    ย์
    0.32
     zám
    0.31
     batas
    0.31
    Act Density 0.006%

    No Known Activations