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

    Neuronpedia

    INDEX
    Explanations

    actions, activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoc
    -0.08
     Entries
    -0.07
    -0.06
    how
    -0.06
    “How
    -0.06
    К
    -0.06
    wrong
    -0.06
    атків
    -0.06
     Foods
    -0.06
    .Information
    -0.06
    POSITIVE LOGITS
    ař
    0.07
    nahme
    0.06
    Repo
    0.06
     работу
    0.06
     cauliflower
    0.06
    ований
    0.06
     OpenGL
    0.06
     queda
    0.06
     searchable
    0.06
     wirk
    0.06
    Act Density 0.577%

    No Known Activations