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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mits
    -0.06
    _Session
    -0.06
     Pars
    -0.06
     goose
    -0.06
    icted
    -0.06
    Vertex
    -0.06
     Prix
    -0.06
    .Yellow
    -0.05
    /Game
    -0.05
     Rw
    -0.05
    POSITIVE LOGITS
    numeric
    0.07
     separates
    0.07
     individual
    0.07
     positively
    0.07
    @$
    0.06
    /import
    0.06
     اتحاد
    0.06
     compil
    0.06
     ПО
    0.06
     По
    0.06
    Act Density 0.203%

    No Known Activations