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

    Neuronpedia

    INDEX
    Explanations

    son

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    력을
    -0.07
     slick
    -0.07
     crossings
    -0.07
    tera
    -0.06
    ００
    -0.06
     outpost
    -0.06
     shoreline
    -0.06
     Kaf
    -0.06
     ActivatedRoute
    -0.06
    Controllers
    -0.06
    POSITIVE LOGITS
     Bin
    0.07
    �
    0.07
    =node
    0.06
     crear
    0.06
     наб
    0.06
    >↵
    0.06
     serviced
    0.06
     зм
    0.06
     Madame
    0.06
     عم
    0.06
    Act Density 0.000%

    No Known Activations