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

    Neuronpedia

    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spring
    -0.06
     году
    -0.06
     важ
    -0.06
    Observable
    -0.06
    ammu
    -0.06
    411
    -0.06
    703
    -0.06
     legion
    -0.06
     annotation
    -0.06
     Myth
    -0.06
    POSITIVE LOGITS
     invers
    0.07
    	RTHOOK
    0.07
     imposed
    0.06
    lander
    0.06
    После
    0.06
    Una
    0.06
    สมเด
    0.06
     ию
    0.06
    	NSString
    0.06
    })↵↵
    0.06
    Act Density 0.154%

    No Known Activations