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

    Neuronpedia

    INDEX
    Explanations

    concat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	game
    -0.07
     Brussels
    -0.07
     Move
    -0.07
    伯
    -0.07
     Rise
    -0.07
     virus
    -0.06
     Relief
    -0.06
     TITLE
    -0.06
     вина
    -0.06
     livro
    -0.06
    POSITIVE LOGITS
     concatenated
    0.11
     concaten
    0.10
    .concat
    0.09
    _concat
    0.09
     Concat
    0.09
     concatenate
    0.08
     truncated
    0.08
    concat
    0.08
    Concat
    0.08
     concat
    0.08
    Act Density 0.004%

    No Known Activations