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

    Neuronpedia

    INDEX
    Explanations

    turned

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	private
    -0.08
    (private
    -0.08
    Contract
    -0.07
     landscaping
    -0.07
     safety
    -0.06
     assessing
    -0.06
    acts
    -0.06
     predictions
    -0.06
    palette
    -0.06
    sqrt
    -0.06
    POSITIVE LOGITS
    pollo
    0.07
    ATFORM
    0.06
     cherche
    0.06
    ام
    0.06
     nor
    0.06
    flake
    0.06
     mú
    0.06
     gunshot
    0.06
     espect
    0.06
     výbě
    0.06
    Act Density 0.009%

    No Known Activations