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

    Neuronpedia

    INDEX
    Explanations

    major

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ragments
    -0.07
    =settings
    -0.07
     secretion
    -0.07
     cih
    -0.07
     Thur
    -0.07
    言い
    -0.06
     організа
    -0.06
    finally
    -0.06
    арат
    -0.06
     گیری
    -0.06
    POSITIVE LOGITS
    	
↵
↵
    0.07
    _reward
    0.07
    """
↵
↵
    0.06
     Sanity
    0.06
    .Virtual
    0.06
    ↵      ↵
    0.06
     اف
    0.06
    .runtime
    0.06
    (color
    0.06
    /live
    0.06
    Act Density 0.023%

    No Known Activations