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

    Neuronpedia

    INDEX
    Explanations

    AK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Lorem
    -0.07
     хорошо
    -0.07
    _PASS
    -0.07
     παρα
    -0.07
     фай
    -0.07
     fullPath
    -0.07
     تور
    -0.06
     Thursday
    -0.06
     معمولا
    -0.06
     lf
    -0.06
    POSITIVE LOGITS
     AK
    0.25
    AK
    0.17
    ak
    0.10
    aks
    0.08
     Dak
    0.07
    ake
    0.07
    advertisement
    0.07
    _ak
    0.07
    inston
    0.07
    addock
    0.07
    Act Density 0.007%

    No Known Activations