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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    left

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    นะนำ
    -0.60
     سكانية
    -0.57
    dération
    -0.57
    ModelSerializer
    -0.56
     ​​
    -0.55
    ientôt
    -0.52
    espół
    -0.52
    Zeneca
    -0.51
    PerformLayout
    -0.51
    lloworld
    -0.50
    POSITIVE LOGITS
    |_{\
    0.83
    \|_{\
    0.80
    ]^{-
    0.76
    \|_{
    0.73
    |^
    0.72
    |^{
    0.71
    \|^{
    0.71
    (||
    0.71
    \|
    0.70
    \|\
    0.70
    Act Density 8.078%

    No Known Activations