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

    Neuronpedia

    INDEX
    Explanations

    say prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =require
    -0.08
     film
    -0.07
    train
    -0.07
     Tcp
    -0.07
     methane
    -0.07
     rejoice
    -0.07
     Butter
    -0.07
    医务人员
    -0.07
     airport
    -0.07
     road
    -0.07
    POSITIVE LOGITS
    ؾ
    0.07
    conscious
    0.07
    rott
    0.07
    	Function
    0.07
    ﭮ
    0.07
    (MethodImplOptions
    0.07
    现今
    0.07
    _TAGS
    0.07
    会在
    0.07
    פן
    0.07
    Act Density 0.320%

    No Known Activations