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

    Neuronpedia

    INDEX
    Explanations

    pronouns for people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tex
    -0.07
     COM
    -0.07
    )$/
    -0.06
    .Resources
    -0.06
    .addClass
    -0.06
    ocab
    -0.06
    Mul
    -0.06
     เช
    -0.06
    .j
    -0.06
    환
    -0.06
    POSITIVE LOGITS
     government
    0.06
    atitude
    0.06
    MessageType
    0.06
     diligently
    0.06
    pizza
    0.06
    going
    0.06
     küt
    0.06
     général
    0.06
     gab
    0.06
    .tiles
    0.06
    Act Density 0.014%

    No Known Activations