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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imm
    -0.06
    thes
    -0.06
     dup
    -0.06
     quantify
    -0.06
     erased
    -0.06
    κα
    -0.06
    зна
    -0.06
    addin
    -0.06
    ýn
    -0.06
    _id
    -0.06
    POSITIVE LOGITS
     Floral
    0.07
     hon
    0.06
     getopt
    0.06
    주시
    0.06
     hoş
    0.06
     Aircraft
    0.06
    ้องน
    0.06
     malt
    0.06
     picking
    0.06
    -worker
    0.06
    Act Density 0.001%

    No Known Activations