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

    Neuronpedia

    INDEX
    Explanations

    personal opinions and thoughts

    oai_token-act-pair · gemini-2.0-flash

    personal opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -1.02
     kasarigan
    -0.96
     تضيفلها
    -0.94
     Italijanski
    -0.90
     שוליים
    -0.89
     betweenstory
    -0.84
    AndEndTag
    -0.84
    IUrlHelper
    -0.79
    Vidite
    -0.79
    IndentedString
    -0.78
    POSITIVE LOGITS
    Zeneca
    0.38
    dua
    0.37
    qui
    0.36
    uens
    0.36
    身を
    0.35
    seitige
    0.33
     को
    0.33
    seitig
    0.33
     take
    0.33
     taken
    0.32
    Act Density 1.462%

    No Known Activations