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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -support
    -0.09
     condições
    -0.08
     affirmed
    -0.08
    -extension
    -0.07
    -conditioned
    -0.07
    -condition
    -0.07
     Joining
    -0.07
    -cur
    -0.07
    -init
    -0.07
     espal
    -0.07
    POSITIVE LOGITS
    实际上
    0.10
     swapped
    0.10
     mis
    0.09
     misl
    0.09
     guise
    0.09
     swapping
    0.09
    retro
    0.09
    .swap
    0.09
     entsprechen
    0.09
     swaps
    0.09
    Act Density 0.039%

    No Known Activations