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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heads
    -0.07
    -manager
    -0.06
     Manus
    -0.06
     INTEGER
    -0.06
    Parts
    -0.06
    LB
    -0.06
    PIPE
    -0.06
    .prop
    -0.06
     underway
    -0.06
    tep
    -0.06
    POSITIVE LOGITS
     sophomore
    0.07
    untary
    0.07
     Anglic
    0.06
    числ
    0.06
     spolu
    0.06
    εύ
    0.06
     haven
    0.06
     सज
    0.06
     classmates
    0.06
     Yosemite
    0.06
    Act Density 0.008%

    No Known Activations