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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wiel
    -0.07
    圣经
    -0.07
    结论
    -0.07
     харак
    -0.06
    COVID
    -0.06
     conscient
    -0.06
    כנ
    -0.06
    PATH
    -0.06
     이것은
    -0.06
    (Set
    -0.06
    POSITIVE LOGITS
    "])↵
    0.08
    employee
    0.08
    Sector
    0.07
                   ↵
    0.07
    touches
    0.07
     دقائق
    0.07
     sleek
    0.07
    services
    0.07
     pulls
    0.07
    ()]);↵
    0.07
    Act Density 0.022%

    No Known Activations