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

    Neuronpedia

    INDEX
    Explanations

    widespread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ULD
    -0.07
    ادية
    -0.07
     italiane
    -0.07
     <!--[
    -0.06
     Ödül
    -0.06
    +)\
    -0.06
    řit
    -0.06
     Sonuç
    -0.06
     Rewrite
    -0.06
     worthy
    -0.06
    POSITIVE LOGITS
     hack
    0.06
    	ent
    0.06
    (url
    0.06
    landers
    0.06
    .device
    0.05
     wondering
    0.05
    ocrat
    0.05
     asks
    0.05
     pale
    0.05
    	arg
    0.05
    Act Density 0.001%

    No Known Activations