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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    say question mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InputTagHelper
    -0.81
    ImageContext
    -0.77
    цездатний
    -0.75
    FormTagHelper
    -0.74
     MainAxisSize
    -0.72
    SceneManagement
    -0.71
     myſelf
    -0.71
     $_"
    -0.69
    EClass
    -0.68
     Theſe
    -0.68
    POSITIVE LOGITS
    ?
    2.86
    ?”
    2.27
    ?"
    2.25
    ？
    2.19
    ?'
    2.14
    ??
    2.09
    ?’
    2.09
     ?
    2.09
    ?)
    2.08
    ?
    2.08
    Act Density 1.686%

    No Known Activations