INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    76
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    concepts related to interpersonal connections and relationships

    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.54
     AssemblyCulture
    -0.52
    $_['
    -0.51
    出版年
    -0.49
     Elector
    -0.49
     surla
    -0.48
     autopilot
    -0.47
    estacks
    -0.47
    úgó
    -0.47
     piezo
    -0.46
    POSITIVE LOGITS
     relationships
    0.69
     amistad
    0.64
     friendships
    0.59
    relationships
    0.57
     friends
    0.54
     relationship
    0.54
     relaciones
    0.54
     Relationships
    0.52
     amizade
    0.52
    Relationships
    0.51
    Act Density 0.001%

    No Known Activations