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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thomas
    -0.06
     Extremely
    -0.06
     helpful
    -0.06
    dao
    -0.06
    Requests
    -0.06
     unicode
    -0.06
    krát
    -0.06
    Their
    -0.06
     dmg
    -0.06
     Yük
    -0.06
    POSITIVE LOGITS
    ็นว
    0.07
    .childNodes
    0.07
    лась
    0.07
     الول
    0.07
     kalk
    0.06
    -panel
    0.06
     receptions
    0.06
    olv
    0.06
    ownt
    0.06
     trying
    0.06
    Act Density 0.027%

    No Known Activations