INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    72
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    expressions of excitement

    New Auto-Interp
    Negative Logits
    $_['
    -0.57
    лтемелер
    -0.54
     AssemblyCulture
    -0.54
    Personendaten
    -0.52
     Wiktionnaire
    -0.51
     verwijzen
    -0.49
    tyimages
    -0.48
    Hochspringen
    -0.48
     Вікі
    -0.48
     gynnwys
    -0.48
    POSITIVE LOGITS
     excitement
    0.56
     exhilarating
    0.56
     thrilling
    0.54
     exciting
    0.52
     thrills
    0.52
     feeling
    0.50
     thrill
    0.48
    feel
    0.48
     exhilar
    0.48
    feels
    0.47
    Act Density 0.000%

    No Known Activations