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

    Neuronpedia

    INDEX
    Explanations

    Internet chat text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .NEW
    -0.06
     salsa
    -0.06
    ystate
    -0.06
    >").
    -0.06
    рой
    -0.06
     Left
    -0.06
     sincerity
    -0.06
     новые
    -0.06
    客
    -0.06
    主
    -0.06
    POSITIVE LOGITS
     annually
    0.07
     binding
    0.07
    	style
    0.07
     travelers
    0.06
     mt
    0.06
    TestMethod
    0.06
    exec
    0.06
    laus
    0.06
     investig
    0.06
     نماید
    0.06
    Act Density 0.022%

    No Known Activations