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

    Neuronpedia

    INDEX
    Explanations

    ;;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }>{
    -0.07
    ности
    -0.06
     ши
    -0.06
     бол
    -0.06
    ح
    -0.06
     от
    -0.06
     прош
    -0.06
     tako
    -0.06
     Fet
    -0.06
    话
    -0.06
    POSITIVE LOGITS
     ;;↵
    0.10
     commun
    0.07
    ;;↵
    0.07
     recruits
    0.07
    Scalar
    0.07
     Rogue
    0.06
    __);↵
    0.06
     mL
    0.06
     Angular
    0.06
    oud
    0.06
    Act Density 0.001%

    No Known Activations