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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    W
    -0.07
    元
    -0.07
     hamstring
    -0.06
     workplaces
    -0.06
     todas
    -0.06
     underground
    -0.06
    viewport
    -0.06
    ození
    -0.06
    _Speed
    -0.06
    -0.06
    POSITIVE LOGITS
     Say
    0.08
    say
    0.08
    Say
    0.07
    ize
    0.07
    /messages
    0.07
    ays
    0.07
     SAY
    0.06
     TRY
    0.06
     (~
    0.06
    AY
    0.06
    Act Density 0.022%

    No Known Activations