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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Riders
    -0.06
     UIF
    -0.06
    อก
    -0.06
     непри
    -0.06
    mention
    -0.06
     letters
    -0.06
    ��
    -0.05
     paddingLeft
    -0.05
    -aut
    -0.05
    าบ
    -0.05
    POSITIVE LOGITS
     maturity
    0.07
    Medical
    0.07
    	Error
    0.07
     Terrorism
    0.06
                
    0.06
     Installed
    0.06
    TimeStamp
    0.06
    uvian
    0.06
    	Matrix
    0.06
     توسعه
    0.06
    Act Density 0.001%

    No Known Activations