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

    Neuronpedia

    INDEX
    Explanations

    references to scientific measurements or indicators in a technical context

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

    after names or locations

    np_acts-logits-general · gemini-2.0-flash

    Kaltbrunn railway station

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    closet
    -0.52
    Bronnen
    -0.50
    CPtr
    -0.49
    bilisi
    -0.49
     isComment
    -0.48
     Closet
    -0.48
     nonUne
    -0.47
     Sadd
    -0.47
    Lähteet
    -0.47
    ackerel
    -0.47
    POSITIVE LOGITS
    w
    0.58
    QtWidgets
    0.56
    URL
    0.54
    userdetails
    0.53
     varietà
    0.53
     nahilalakip
    0.53
     umano
    0.53
    viale
    0.52
    uxxxx
    0.52
     urine
    0.52
    Act Density 0.595%

    No Known Activations