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

    Neuronpedia

    INDEX
    Explanations

    desire to rule

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terrified
    -0.07
     receipt
    -0.07
    Ἁ
    -0.07
    سئل
    -0.06
     reluctant
    -0.06
     subsid
    -0.06
    .resources
    -0.06
    SELECT
    -0.06
     Riverside
    -0.06
    ţi
    -0.06
    POSITIVE LOGITS
     Dest
    0.07
    _cr
    0.06
    橞
    0.06
     Clover
    0.06
    ulus
    0.06
    nock
    0.06
    真空
    0.06
    ıkl
    0.06
     gr
    0.06
     }>↵
    0.06
    Act Density 0.046%

    No Known Activations