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

    Neuronpedia

    INDEX
    Explanations

    references to actors

    oai_token-act-pair · gemini-2.0-flash

    actors and roles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.67
    principalColumn
    -0.60
    tagHelperRunner
    -0.60
    رشف
    -0.57
     Audiodateien
    -0.56
    κτή
    -0.54
    ividual
    -0.54
    CreateModel
    -0.53
    complexContent
    -0.52
    WithIOException
    -0.52
    POSITIVE LOGITS
    interopRequire
    0.67
    playing
    0.61
     sebagai
    0.57
     playing
    0.56
     thiên
    0.53
    Plays
    0.53
     Spoilers
    0.52
     ως
    0.51
     plays
    0.50
     jako
    0.49
    Act Density 1.797%

    No Known Activations