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

    Neuronpedia

    INDEX
    Explanations

    words related to marketing and improving your website

    oai_token-act-pair · gemini-2.0-flash

    End of titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.75
     Jefus
    -0.73
     purpoſe
    -0.70
     ſche
    -0.69
     Diſ
    -0.69
     greateſt
    -0.68
     Shakspeare
    -0.68
     Monfieur
    -0.66
     preſent
    -0.66
     reaſon
    -0.65
    POSITIVE LOGITS
     hal
    0.52
    intele
    0.48
    Viited
    0.48
     متعلقه
    0.47
     qu
    0.47
    нью
    0.46
     cub
    0.45
     se
    0.45
     poste
    0.45
    ToRefresh
    0.45
    Act Density 2.144%

    No Known Activations