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

    Neuronpedia

    INDEX
    Explanations

    OF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	It
    -0.06
     ic
    -0.06
     Koch
    -0.06
    .KeyChar
    -0.06
     mnist
    -0.06
     ComponentFixture
    -0.06
    ana
    -0.06
     Federation
    -0.06
    .website
    -0.06
    ookeeper
    -0.06
    POSITIVE LOGITS
    ülebilir
    0.07
     RECE
    0.06
     permissible
    0.06
     overcoming
    0.06
     chants
    0.06
     osm
    0.06
     pok
    0.06
    areas
    0.06
     الأمر
    0.06
     pharmac
    0.06
    Act Density 0.002%

    No Known Activations