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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     survey
    -0.08
     surveys
    -0.07
     đáo
    -0.06
     pounded
    -0.06
     halt
    -0.06
     massac
    -0.06
     necessarily
    -0.06
     İslam
    -0.06
    ृ
    -0.06
     separate
    -0.06
    POSITIVE LOGITS
    投注
    0.07
     δεν
    0.06
     Teh
    0.06
    enting
    0.06
     zprávy
    0.06
     lọc
    0.06
     Miles
    0.06
    (da
    0.06
     Founder
    0.06
    (*
    0.06
    Act Density 0.000%

    No Known Activations