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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    VIRTUAL
    -0.07
    非常高
    -0.07
    になります
    -0.07
    及其他
    -0.07
     dusk
    -0.06
     출력
    -0.06
    uego
    -0.06
    عضو
    -0.06
     öğrenci
    -0.06
     correctly
    -0.06
    POSITIVE LOGITS
    SOC
    0.07
    dont
    0.07
     t
    0.07
     ZZ
    0.06
    LOC
    0.06
     collective
    0.06
    	new
    0.06
    衮
    0.06
    	Response
    0.06
    𝚋
    0.06
    Act Density 0.182%

    No Known Activations