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

    Neuronpedia

    INDEX
    Explanations

    proceed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ЕН
    -0.06
    Decl
    -0.06
    Wall
    -0.06
     Sanat
    -0.06
     jako
    -0.06
    .f
    -0.06
    ymax
    -0.06
     EMP
    -0.06
    атив
    -0.06
    满
    -0.06
    POSITIVE LOGITS
     pd
    0.06
    [strlen
    0.06
    	Output
    0.06
     /[
    0.06
     tackled
    0.06
     thuisontvangst
    0.06
     conna
    0.06
    pd
    0.06
     lỗ
    0.06
     tiles
    0.06
    Act Density 0.000%

    No Known Activations