INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    64.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to legal concepts

    New Auto-Interp
    Negative Logits
    Personendaten
    -0.56
    WriteTagHelper
    -0.50
    bentar
    -0.48
    PickerController
    -0.42
     Audiodateien
    -0.41
     eigentlichen
    -0.41
    Aholisi
    -0.41
    oredCriteria
    -0.41
    ChildScrollView
    -0.41
     незавершена
    -0.40
    POSITIVE LOGITS
     lawyer
    0.60
     law
    0.58
     hukum
    0.57
    law
    0.55
    lawyer
    0.53
     Hukum
    0.52
     lawyers
    0.52
     juridique
    0.52
    Law
    0.50
     LAW
    0.50
    Act Density 0.000%

    No Known Activations