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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     управління
    -0.07
    Interop
    -0.07
     использ
    -0.07
    cznie
    -0.07
     Florence
    -0.06
     Innoc
    -0.06
    chluss
    -0.06
     трансп
    -0.06
    ểm
    -0.06
     Glouce
    -0.06
    POSITIVE LOGITS
     say
    0.16
     said
    0.16
     saying
    0.14
     says
    0.14
     SAY
    0.12
    Say
    0.12
     Say
    0.12
    say
    0.11
    said
    0.11
     Said
    0.11
    Act Density 0.085%

    No Known Activations