INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    69
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    words related to journeys and navigation

    New Auto-Interp
    Negative Logits
    /*++
    -0.43
     święta
    -0.42
     barata
    -0.39
    $_['
    -0.38
     <>",
    -0.36
     commonest
    -0.36
    Biological
    -0.35
     maxn
    -0.34
     виправивши
    -0.34
     gron
    -0.34
    POSITIVE LOGITS
     journey
    0.62
    
    0.59
    journey
    0.56
     journeys
    0.54
    ValueStyle
    0.52
     direction
    0.52
     directions
    0.50
     walk
    0.49
     hướng
    0.49
     JOURNEY
    0.49
    Act Density 0.002%

    No Known Activations