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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ens
    -0.07
    יצ
    -0.07
     list
    -0.07
     corres
    -0.07
    إنش
    -0.07
     classical
    -0.07
    ServletResponse
    -0.07
    api
    -0.06
    	context
    -0.06
    놔
    -0.06
    POSITIVE LOGITS
     -------
    0.07
     pharmacist
    0.07
     Therm
    0.07
     scrub
    0.07
    磅
    0.07
     пло
    0.07
    volution
    0.07
     Phon
    0.07
     futures
    0.07
     마
    0.06
    Act Density 0.017%

    No Known Activations