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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rooms
    -0.07
    .ByteArray
    -0.07
    enedor
    -0.06
    (ap
    -0.06
     nights
    -0.06
    Ａ
    -0.06
     승
    -0.06
     сф
    -0.06
    iban
    -0.06
     Sonia
    -0.06
    POSITIVE LOGITS
     pově
    0.07
     siè
    0.06
     deutsche
    0.06
     ekonom
    0.06
     mathematical
    0.06
    (IL
    0.06
     التج
    0.06
    CL
    0.06
    jj
    0.06
     清
    0.06
    Act Density 0.003%

    No Known Activations