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

    Neuronpedia

    INDEX
    Explanations

    language around gift recommendations for helping professions

    oai_token-act-pair · gemini-2.0-flash

    gift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     виправивши
    -0.80
     ModelExpression
    -0.75
    /*
    -0.62
    GIVEREF
    -0.60
    shadowRadius
    -0.60
    Vidite
    -0.60
    rhosis
    -0.59
    ValueGeneration
    -0.58
     дописавши
    -0.58
    CppCodeGen
    -0.58
    POSITIVE LOGITS
    RenderAtEndOf
    0.50
     hưởng
    0.48
    FormTagHelper
    0.48
    odal
    0.47
    anovic
    0.46
     learned
    0.46
     pro
    0.46
    ,:),
    0.46
     letti
    0.45
     pov
    0.44
    Act Density 1.294%

    No Known Activations