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

    Neuronpedia

    INDEX
    Explanations

    king

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aligned
    -0.07
     won
    -0.07
    .items
    -0.07
     towards
    -0.06
     gather
    -0.06
          ↵      ↵
    -0.06
     encounter
    -0.06
     Fs
    -0.06
     transforming
    -0.06
     improve
    -0.06
    POSITIVE LOGITS
    爱情
    0.07
    开采
    0.07
    _NT
    0.07
    กา
    0.07
    SCALL
    0.06
     Atlantis
    0.06
    售票
    0.06
    /material
    0.06
     clever
    0.06
    _BOOT
    0.06
    Act Density 0.000%

    No Known Activations