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

    Neuronpedia

    INDEX
    Explanations

    logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     정
    -0.08
     прик
    -0.07
    類
    -0.07
     technik
    -0.07
    部屋
    -0.07
    ách
    -0.06
    정
    -0.06
    genic
    -0.06
     stash
    -0.06
     wird
    -0.06
    POSITIVE LOGITS
     Lem
    0.07
     Polish
    0.06
     Illustr
    0.06
    .intellij
    0.06
    ][
    0.06
    oultry
    0.06
     ];
    0.06
     superheroes
    0.06
    ]').
    0.06
     NSUInteger
    0.06
    Act Density 0.010%

    No Known Activations