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

    Neuronpedia

    INDEX
    Explanations

    references to choices and alternatives

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

    choices and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uğ
    -0.37
     pieles
    -0.32
     interesan
    -0.31
     Améli
    -0.30
     periodistas
    -0.30
     bomberos
    -0.30
     namorado
    -0.29
     calendrier
    -0.29
     kekasih
    -0.29
     atriz
    -0.28
    POSITIVE LOGITS
     مشين
    0.82
     esternos
    0.77
     pinulongan
    0.76
     Autorizaciones
    0.75
     propOrder
    0.75
     defaultstate
    0.74
    DoubleQuotes
    0.72
    SequentialGroup
    0.71
    aarrggbb
    0.70
     autorytatywna
    0.68
    Act Density 0.026%

    No Known Activations