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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forest
    -0.07
     iid
    -0.06
    idency
    -0.06
     پایین
    -0.06
     mö
    -0.06
    (IT
    -0.06
     deutschland
    -0.06
    ergency
    -0.06
     independence
    -0.06
     gdzie
    -0.06
    POSITIVE LOGITS
     angels
    0.07
    جميع
    0.07
    照片
    0.07
    78
    0.07
     Modular
    0.06
    (record
    0.06
    อส
    0.06
     arresting
    0.06
     boz
    0.06
    =rand
    0.06
    Act Density 0.000%

    No Known Activations