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

    Neuronpedia

    INDEX
    Explanations

    etric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fol
    -0.06
    τολ
    -0.06
    	diff
    -0.06
    ادل
    -0.06
    (descriptor
    -0.06
     мереж
    -0.06
     Ал
    -0.06
    、高
    -0.06
    ادية
    -0.06
     худож
    -0.05
    POSITIVE LOGITS
     feminism
    0.07
     mood
    0.07
     True
    0.07
    ribly
    0.07
     Knicks
    0.06
     Wi
    0.06
     전세가
    0.06
    河
    0.06
    _typeDefinitionSize
    0.06
     पर
    0.06
    Act Density 0.002%

    No Known Activations